© 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. 111057
    Prev
    Next
    INDEX
    Explanations

    Bod / BOD / Bodily prefixes

    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
    体
    0.45
     lichaam
    0.42
    มีการ
    0.41
    体的
    0.41
    body
    0.40
    рованного
    0.39
    腔
    0.37
    铯
    0.36
    jir
    0.36
    abwe
    0.36
    POSITIVE LOGITS
    𝔸
    0.43
     Went
    0.40
     bağ
    0.40
    NAR
    0.40
    wydd
    0.40
    GRU
    0.40
    VAR
    0.39
    atiu
    0.39
    Went
    0.38
    Stuart
    0.38
    Activations Density 0.003%

    No Known Activations