© 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. 34-GEMMASCOPE-RES-131K
    7. 33251
    Prev
    Next
    INDEX
    Explanations

    code and file names

    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_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
    圍
    -0.71
    싹
    -0.71
    vers
    -0.69
    indale
    -0.66
    urry
    -0.66
    yeth
    -0.66
    ohar
    -0.66
    cf
    -0.66
     Ueb
    -0.65
    kin
    -0.65
    POSITIVE LOGITS
    カラー
    0.70
     Birch
    0.70
     selera
    0.69
    Hig
    0.69
    kå
    0.67
    Zx
    0.66
     רצ
    0.63
     aéro
    0.63
     normalization
    0.62
    Sant
    0.62
    Activations Density 0.042%

    No Known Activations