© 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. 25148
    Prev
    Next
    INDEX
    Explanations

    free, wild, control, dominant

    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
    ⵍ
    0.50
    ระบบ
    0.46
    扡
    0.46
     대체
    0.46
    unstyled
    0.45
    ափ
    0.43
     ഫ
    0.43
     ff
    0.43
     डीपी
    0.43
     ikke
    0.43
    POSITIVE LOGITS
    Food
    0.38
    !
    0.37
    ounce
    0.36
    tee
    0.36
     potrav
    0.36
     Food
    0.36
    Investment
    0.36
    Hue
    0.36
    Jay
    0.35
    Stuart
    0.35
    Activations Density 0.003%

    No Known Activations