© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8578
    Prev
    Next
    INDEX
    Explanations

    document sections or summaries

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viêm
    0.46
     nước
    0.42
     attrs
    0.42
     fauc
    0.38
     droplets
    0.38
    {},
    0.37
     rất
    0.36
     densément
    0.36
    一批
    0.36
    🟥
    0.36
    POSITIVE LOGITS
    Solution
    0.45
     Conclusion
    0.42
    Conclusion
    0.41
     História
    0.40
    Discussion
    0.40
     Methodology
    0.40
    Synopsis
    0.39
    Strategy
    0.39
     Результа
    0.39
    Rationale
    0.39
    Activations Density 0.043%

    No Known Activations