© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32616
    Prev
    Next
    INDEX
    Explanations

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sometime
    0.36
     ہوسکتا
    0.36
    avacan
    0.36
    🛡
    0.35
     způso
    0.35
    beiter
    0.34
     सकता
    0.34
    毖
    0.34
    лён
    0.34
    롯
    0.34
    POSITIVE LOGITS
     complete
    0.43
     combine
    0.43
     main
    0.42
     initState
    0.41
     iterative
    0.41
     entire
    0.40
    MainActivity
    0.38
     composite
    0.38
    まとめ
    0.38
    Init
    0.38
    Activations Density 0.087%

    No Known Activations