© 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. 33491
    Prev
    Next
    INDEX
    Explanations

    institution names and abbreviations

    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
     jong
    -0.82
     frambo
    -0.81
    intendo
    -0.79
    ɟ
    -0.74
     jongen
    -0.74
    lagu
    -0.73
    ſon
    -0.72
    vertible
    -0.71
     دان
    -0.71
    pry
    -0.68
    POSITIVE LOGITS
     Claremont
    1.04
     Pomona
    0.97
     Upland
    0.93
     zeroes
    0.78
     RRP
    0.77
     полі
    0.75
    Поэтому
    0.74
    uresh
    0.73
    neux
    0.72
    zw
    0.72
    Activations Density 0.022%

    No Known Activations