© 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. 10-GEMMASCOPE-RES-131K
    7. 40966
    Prev
    Next
    INDEX
    Explanations

    N-day or N days

    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_10/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
    </strong>
    -2.38
    </h4>
    -2.22
     während
    -2.11
    抡
    -2.00
    拚
    -1.89
    </h1>
    -1.88
     În
    -1.88
    やう
    -1.84
     Directly
    -1.81
     Previous
    -1.77
    POSITIVE LOGITS
    你
    2.47
     erros
    1.99
    ஂ
    1.95
    諼
    1.89
    鯢
    1.88
    ꦲ
    1.86
    ！！
    1.84
     itſelf
    1.84
    注意事
    1.82
    ！！！！
    1.77
    Activations Density 0.011%

    No Known Activations