© 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. 34-GEMMASCOPE-RES-131K
    7. 914
    Prev
    Next
    INDEX
    Explanations

    New Yorker stories

    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
     NPR
    -1.05
    NPR
    -0.88
    zló
    -0.76
    mė
    -0.75
     Mic
    -0.73
     ahorro
    -0.69
     Salon
    -0.69
    )}-\
    -0.69
    ERR
    -0.69
     Jock
    -0.68
    POSITIVE LOGITS
     Mummy
    0.76
     flot
    0.74
    herz
    0.73
    cales
    0.72
    balls
    0.71
     corde
    0.71
     borde
    0.70
    路的
    0.69
    гъл
    0.69
    鑾
    0.69
    Activations Density 0.036%

    No Known Activations