© 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. 84338
    Prev
    Next
    INDEX
    Explanations

    reserved for catalysts

    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
    厥
    0.39
    arnath
    0.37
     dg
    0.36
    grounds
    0.35
    გრამ
    0.34
    로그
    0.34
     منها
    0.34
    OLS
    0.34
    苦手
    0.33
    γεν
    0.33
    POSITIVE LOGITS
     energía
    0.44
    胡
    0.40
     Unde
    0.39
     energije
    0.39
     Gund
    0.38
    लित
    0.38
     Gull
    0.38
     Delicate
    0.38
     Feel
    0.38
     दुनियाभर
    0.37
    Activations Density 0.000%

    No Known Activations