© 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. 98711
    Prev
    Next
    INDEX
    Explanations

    actions you or someone else took

    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
     capricious
    0.44
     retarded
    0.40
     horizontal
    0.39
     an
    0.38
    혁
    0.38
     cellspacing
    0.37
    celes
    0.37
     Helvetica
    0.36
     convective
    0.35
    leta
    0.34
    POSITIVE LOGITS
    垭
    0.39
     Minist
    0.39
    🤌
    0.39
     சாலை
    0.39
    ⺠
    0.38
    თვის
    0.38
     OKC
    0.38
     በሚ
    0.38
    হত
    0.38
    ِمض
    0.37
    Activations Density 0.003%

    No Known Activations