© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117336
    Prev
    Next
    INDEX
    Explanations

    quotes, titles, or questions

    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
     Kiki
    -0.76
     Vidya
    -0.73
     Frente
    -0.71
     bral
    -0.70
    amey
    -0.69
     tướng
    -0.68
     Шта
    -0.68
    gerton
    -0.68
     PCM
    -0.67
     Obi
    -0.66
    POSITIVE LOGITS
     ASSOCIATION
    0.82
     Espanha
    0.77
     Association
    0.77
     ассо
    0.75
     незакон
    0.75
    Mono
    0.74
    association
    0.73
    Gateway
    0.73
     hunters
    0.73
    Association
    0.72
    Activations Density 0.020%

    No Known Activations