© 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. 2494
    Prev
    Next
    INDEX
    Explanations

    classification labels and descriptions

    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
    inns
    -0.93
     Camin
    -0.82
    castle
    -0.73
    platforms
    -0.73
     darauf
    -0.71
     jamón
    -0.70
     замок
    -0.70
    ➟
    -0.69
     Helmet
    -0.69
    Browse
    -0.69
    POSITIVE LOGITS
    шої
    0.86
    getVersion
    0.82
    ▎
    0.75
     você
    0.74
     Southwestern
    0.74
    llc
    0.71
    axs
    0.71
    urrection
    0.69
     máximo
    0.67
    ₾
    0.66
    Activations Density 0.009%

    No Known Activations