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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10674
    Prev
    Next
    INDEX
    Explanations

    `It says`

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

    The neuron fires on semantically rich content words (nouns, verbs, and adjectives carrying real meaning) rather than on common function words.

    oai_token-act-pair · o4-miniTriggered 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
     BEAUT
    0.65
     (
    0.62
     Zoo
    0.58
     Pueblo
    0.57
    ",
    0.57
     \
    0.55
     N
    0.55
     SUN
    0.55
     TA
    0.54
     persoon
    0.54
    POSITIVE LOGITS
     тако
    0.82
    Ха
    0.74
     പിന്തുണ
    0.74
    Asimismo
    0.73
    瞅
    0.72
     मूवी
    0.71
    rounder
    0.70
     melakukannya
    0.67
     способен
    0.66
     likewise
    0.65
    Activations Density 1.313%

    No Known Activations