© 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-65K
    7. 13976
    Prev
    Next
    INDEX
    Explanations

    Someone performing actions

    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_65k_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
    ;
    0.58
    ตัวเอง
    0.55
    rs
    0.52
    !
    0.48
    ؛
    0.48
    টাই
    0.47
     anything
    0.46
    ?
    0.45
    ),
    0.44
     itself
    0.44
    POSITIVE LOGITS
     Somebody
    0.56
    ങ്കിലും
    0.54
    Somebody
    0.52
     quelqu
    0.51
     Someone
    0.51
     ఎవ
    0.49
     іх
    0.49
     sete
    0.49
    Someone
    0.48
     gás
    0.47
    Activations Density 0.053%

    No Known Activations