© 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. 71002
    Prev
    Next
    INDEX
    Explanations

    a place in

    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
    はなく
    -1.72
    ܊
    -1.66
     diariamente
    -1.59
    ڧ
    -1.57
    見えます
    -1.57
    
    -1.57
    endedor
    -1.56
     rempliss
    -1.55
     Thiết
    -1.53
    廡
    -1.53
    POSITIVE LOGITS
    n
    2.08
     in
    2.03
    p
    1.82
    even
    1.70
    and
    1.65
    ok
    1.63
    at
    1.55
    il
    1.55
    oy
    1.55
    er
    1.50
    Activations Density 0.031%

    No Known Activations