© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35112
    Prev
    Next
    INDEX
    Explanations

    error handling and returns

    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_22/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
    kär
    -1.03
    lás
    -1.03
    avoit
    -1.02
    częściej
    -0.99
    indahan
    -0.98
    lepiej
    -0.95
    Składniki
    -0.95
     parfois
    -0.94
    tween
    -0.93
    delingen
    -0.92
    POSITIVE LOGITS
     so
    0.99
    代わりに
    0.96
     leve
    0.95
     arranque
    0.95
     installer
    0.94
    bootstrap
    0.93
    饋
    0.91
     zamiast
    0.89
     السود
    0.88
    fatal
    0.88
    Activations Density 0.014%

    No Known Activations