© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13571
    Prev
    Next
    INDEX
    Explanations

    questions about you and me

    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_40_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
    4
    0.36
    3
    0.33
     using
    0.33
     ubiqu
    0.33
     עבור
    0.32
     regarding
    0.32
    8
    0.32
     within
    0.31
    Bridge
    0.31
     for
    0.30
    POSITIVE LOGITS
    kuu
    0.31
     tellement
    0.31
     ঘে
    0.30
    ,!
    0.30
    ˏ
    0.29
    <0x81>
    0.29
    ಗ್ಗೆ
    0.29
    ſſ
    0.29
    ゜
    0.29
    MathMarks
    0.29
    Activations Density 0.003%

    No Known Activations