© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16196
    Prev
    Next
    INDEX
    Explanations

    code or mathematical notation beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    帑
    -0.81
    Chron
    -0.80
    Www
    -0.78
    msc
    -0.75
    Industrial
    -0.73
    ὠ
    -0.73
    ırken
    -0.73
     soleil
    -0.72
    imbo
    -0.71
    vertebrates
    -0.71
    POSITIVE LOGITS
     where
    0.74
     consists
    0.72
     probably
    0.72
     ビル
    0.71
     arguably
    0.70
     perhaps
    0.69
     possibly
    0.69
     describes
    0.68
     menciona
    0.68
    “
    0.68
    Activations Density 0.424%

    No Known Activations