© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107080
    Prev
    Next
    INDEX
    Explanations

    animation, photos, default, contract, name

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

    The neuron strongly fires on structural or metadata tokens – things like URL/path separators ("/"), HTML tags or attribute names (“html”, “library”), configuration keys (“default”), and other non-continuous prose items rather than ordinary running text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    rounding
    -0.76
    flour
    -0.73
    fluent
    -0.72
    idigung
    -0.72
     trơn
    -0.71
     Parenthood
    -0.69
     Veterin
    -0.68
    fich
    -0.68
    เที่ยว
    -0.68
     המש
    -0.67
    POSITIVE LOGITS
     Torrey
    0.74
    gé
    0.68
     trembling
    0.68
     interesados
    0.68
     Parish
    0.66
     determinada
    0.65
    SLP
    0.64
    语文
    0.64
     store
    0.63
    enia
    0.63
    Activations Density 0.050%

    No Known Activations