© 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. 30462
    Prev
    Next
    INDEX
    Explanations

    strong or weak qualifiers

    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
    팡
    -0.78
    Zhong
    -0.76
    Zhou
    -0.73
    BITDA
    -0.72
    ฌ
    -0.72
     migh
    -0.71
     boba
    -0.70
     ready
    -0.69
     presentaron
    -0.69
    λά
    -0.68
    POSITIVE LOGITS
     interact
    0.86
     andar
    0.85
    ref
    0.85
    sedur
    0.76
    LEBR
    0.76
    도록
    0.76
    gidas
    0.75
    弱
    0.75
     {?>
    0.75
     abortion
    0.75
    Activations Density 0.037%

    No Known Activations