© 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. 116226
    Prev
    Next
    INDEX
    Explanations

    Bubba Watson, Puppeteer, pupiform

    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
     Köl
    -0.81
    release
    -0.75
    рк
    -0.75
    лект
    -0.75
     Fabri
    -0.73
    康
    -0.73
     beach
    -0.72
     visualization
    -0.71
    complex
    -0.71
     explosion
    -0.71
    POSITIVE LOGITS
    Evelyn
    0.82
    tainers
    0.77
    轶
    0.73
     Internazionale
    0.73
    たぶん
    0.73
    ioc
    0.72
    哋
    0.71
    蠵
    0.70
    penis
    0.70
    　＊
    0.70
    Activations Density 0.015%

    No Known Activations