© 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. 82996
    Prev
    Next
    INDEX
    Explanations

    email addresses and URLs

    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
    wordpress
    -1.14
    gmail
    -1.13
    Vaata
    -1.04
     réessayer
    -0.88
     nič
    -0.85
    ὖ
    -0.83
    Efe
    -0.82
     gmail
    -0.82
    ración
    -0.78
    entlich
    -0.78
    POSITIVE LOGITS
     emplea
    1.05
    므
    0.94
    づらい
    0.93
    diente
    0.87
    وين
    0.83
    pidos
    0.82
     "+
    0.79
    одно
    0.77
    pido
    0.77
     deportiva
    0.75
    Activations Density 0.042%

    No Known Activations