© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103134
    Prev
    Next
    INDEX
    Explanations

    Clayton, Ottawa, Fender, Bios

    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
    кса
    -0.84
    𝔡
    -0.72
    nius
    -0.72
    ɳ
    -0.72
    май
    -0.71
     Нов
    -0.71
     Mutable
    -0.70
     Torah
    -0.69
    DIO
    -0.69
    neiden
    -0.69
    POSITIVE LOGITS
    Michigan
    0.79
     Ottawa
    0.79
     ofrece
    0.77
    mengen
    0.74
     Nate
    0.73
    AddColumn
    0.73
    Nate
    0.73
    ሑ
    0.72
     Herrick
    0.69
    !).
    0.69
    Activations Density 0.009%

    No Known Activations