© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 2847
    Prev
    Next
    INDEX
    Explanations

    little describing quantity or difficulty

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on diminutive or “small” cues—especially the word “little” (and related tiny‐scale nouns like “baby,” “piece,” “things”), marking references that emphasize smallness or affection.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "little" (or variations like "Little") when it appears before nouns.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    uses of the diminutive adjective/quantifier “little,” especially when it modifies a following noun or marks a small degree as a quantifier.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ното
    0.66
     Andere
    0.63
    s
    0.60
     крайне
    0.59
    "><
    0.59
    φος
    0.59
    ের
    0.58
     መካከል
    0.58
     Viel
    0.57
     వెంటనే
    0.57
    POSITIVE LOGITS
     bit
    1.13
    ずつ
    0.81
    bit
    0.78
     കൂടി
    0.77
     birdie
    0.76
     endian
    0.75
    씩
    0.74
     booklet
    0.71
    Endian
    0.71
     länger
    0.68
    Activations Density 0.113%

    No Known Activations