© 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. 93308
    Prev
    Next
    INDEX
    Explanations

    to permit actions or rights

    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
     down
    -0.88
    ardown
    -0.76
    ಿದ
    -0.74
    क्रम
    -0.71
    有意思
    -0.71
    cosmic
    -0.70
    Cosmic
    -0.69
     Fix
    -0.68
     интересно
    -0.67
     conmigo
    -0.67
    POSITIVE LOGITS
    Rosen
    0.78
     Breen
    0.68
     ente
    0.67
    Smart
    0.66
     consign
    0.66
    花
    0.64
    Return
    0.64
    アタ
    0.64
    wala
    0.63
    RAD
    0.63
    Activations Density 0.074%

    No Known Activations