© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30273
    Prev
    Next
    INDEX
    Explanations

    @page, @model, @using

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

    The neuron strongly activates on numeric tokens (raw numbers, version numbers, line counts, etc.) in code and markup.

    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
    ₂
    -0.88
    aments
    -0.85
     whereas
    -0.84
    歩き
    -0.84
     Versus
    -0.81
    也可
    -0.81
    should
    -0.80
     sieben
    -0.78
    ją
    -0.78
     kemudian
    -0.75
    POSITIVE LOGITS
    klärt
    0.75
    渡辺
    0.74
     foggy
    0.73
     народ
    0.73
    ポスト
    0.72
     Himmel
    0.70
    guia
    0.70
     Decisions
    0.70
     gente
    0.70
     extrapolation
    0.69
    Activations Density 0.001%

    No Known Activations