© 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. 22-GEMMASCOPE-RES-131K
    7. 25940
    Prev
    Next
    INDEX
    Explanations

    success rates and outcomes

    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_22/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
    拊
    -2.50
    ￪
    -2.31
    口碑
    -2.31
     fantastic
    -2.30
    全程
    -2.25
     he
    -2.25
    等我
    -2.25
     неболь
    -2.14
    越是
    -2.13
     incredibly
    -2.05
    POSITIVE LOGITS
     که
    3.16
    that
    2.88
    In
    2.81
     Undoubtedly
    2.73
    這
    2.67
    他们
    2.45
    Of
    2.38
    𓋼
    2.34
    他
    2.34
    他们的
    2.33
    Activations Density 0.009%

    No Known Activations