© 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. 224264
    Prev
    Next
    INDEX
    Explanations

    words that precede lists or items

    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
    ([],
    0.44
    ነት
    0.41
    粥
    0.39
     prescribe
    0.39
    Declare
    0.38
    },-
    0.38
     booze
    0.38
    ມື
    0.37
    islang
    0.37
    饉
    0.37
    POSITIVE LOGITS
     Ched
    0.39
    getTable
    0.39
    cta
    0.39
     kaj
    0.38
    umbers
    0.38
    须知
    0.36
     גי
    0.36
    仪表
    0.36
    indle
    0.36
    uzioni
    0.36
    Activations Density 0.000%

    No Known Activations