© 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. 10-GEMMASCOPE-RES-131K
    7. 101993
    Prev
    Next
    INDEX
    Explanations

    mainly followed by X

    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_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
    "}}>
    -3.25
    sandalia
    -2.73
    _),
    -2.69
    ными
    -2.55
    '){
    -2.38
    甞
    -2.38
    
    -2.33
    '));
    -2.28
    йна
    -2.27
    ":
    -2.25
    POSITIVE LOGITS
    re
    3.72
    t
    3.33
    is
    3.13
    en
    2.94
    up
    2.80
    y
    2.80
    a
    2.77
    at
    2.75
    e
    2.53
     sorta
    2.50
    Activations Density 0.009%

    No Known Activations