© 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. 63990
    Prev
    Next
    INDEX
    Explanations

    Kl Kl Kl Kl Kl

    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
    webb
    -0.79
     helt
    -0.72
     таблетки
    -0.71
     одним
    -0.69
     песня
    -0.69
     penetrated
    -0.69
    ホルダー
    -0.69
    evo
    -0.68
    YZ
    -0.68
    ínez
    -0.67
    POSITIVE LOGITS
    Suppose
    0.79
     supposes
    0.75
    Kirk
    0.75
    iempos
    0.73
     Suppose
    0.73
     endlessly
    0.71
     shales
    0.71
     pieni
    0.71
    重大
    0.70
    専
    0.70
    Activations Density 0.032%

    No Known Activations