© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75046
    Prev
    Next
    INDEX
    Explanations

    labels for specific data points

    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
     pérd
    -1.78
    饜
    -1.73
     favoris
    -1.67
    蹓
    -1.66
    ſu
    -1.60
    ñales
    -1.59
    킁
    -1.56
    쐈
    -1.56
     レスト
    -1.55
     vôtre
    -1.52
    POSITIVE LOGITS
     in
    1.93
     for
    1.83
    n
    1.77
    ,
    1.69
    d
    1.64
    o
    1.58
    g
    1.54
     to
    1.52
    in
    1.51
    at
    1.50
    Activations Density 0.022%

    No Known Activations