© 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. 20149
    Prev
    Next
    INDEX
    Explanations

    numbers and times

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

    numbers and time spans

    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
    FFECT
    0.41
     ನನ್ನ
    0.40
    whether
    0.40
     僕
    0.40
     스스로
    0.39
     _{\
    0.38
     直接
    0.37
    ✋
    0.37
     無
    0.37
     благодар
    0.37
    POSITIVE LOGITS
    夲
    0.50
    நாயகம்
    0.45
    を活用
    0.43
     prélim
    0.43
     डिप्लो
    0.42
    旨在
    0.42
    ாவும்
    0.42
    രിച്ചത്
    0.42
    情报
    0.42
     رجسٹریشن
    0.42
    Activations Density 0.000%

    No Known Activations