© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103507
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific items

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

    The neuron detects names of onion‐family or similar pungent cooking ingredients (e.g. scallion, chives, garlic).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    入り口
    -1.92
    筧
    -1.67
    PTEMBER
    -1.64
    古屋
    -1.63
     pouvait
    -1.62
     Dois
    -1.61
     Mú
    -1.59
     будешь
    -1.55
    吉田
    -1.52
     éx
    -1.52
    POSITIVE LOGITS
    an
    1.94
    ?"
    1.80
    k
    1.77
    z
    1.67
    v
    1.66
    ות
    1.65
     [
    1.59
     –
    1.56
     see
    1.55
     speculated
    1.52
    Activations Density 0.012%

    No Known Activations