© 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. 117662
    Prev
    Next
    INDEX
    Explanations

    canadian organizations and groups

    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
     裕
    -0.87
     conifers
    -0.83
    蓼
    -0.82
    ⌃
    -0.80
    JAL
    -0.77
    قيم
    -0.75
    certificates
    -0.73
     corolla
    -0.73
     الأولى
    -0.73
     脸
    -0.73
    POSITIVE LOGITS
    rą
    0.76
     Pferd
    0.72
    実は
    0.72
     Reviewed
    0.71
    会い
    0.70
     人形
    0.70
    遞
    0.69
    士
    0.68
    Normally
    0.68
    bsd
    0.68
    Activations Density 0.013%

    No Known Activations