© 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. 98865
    Prev
    Next
    INDEX
    Explanations

    code file headers or comments

    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
    glClear
    -0.78
    vensis
    -0.75
    olge
    -0.75
     pokoje
    -0.73
    mene
    -0.71
    ๕
    -0.71
    厲
    -0.71
     вещи
    -0.70
    Là
    -0.70
     vendedor
    -0.69
    POSITIVE LOGITS
     Pallas
    0.91
    inafter
    0.82
    Editora
    0.79
     lus
    0.79
     צו
    0.79
    Perfection
    0.78
    後期
    0.77
     Sutra
    0.76
     valentino
    0.75
     papp
    0.75
    Activations Density 0.044%

    No Known Activations