© 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-262K
    7. 36094
    Prev
    Next
    INDEX
    Explanations

    finally,

    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_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
     stesse
    0.54
     stessi
    0.52
     milestones
    0.51
    *;
    0.49
    -,
    0.48
    uanya
    0.48
     paralyzed
    0.48
     (^
    0.47
     interchanges
    0.47
    лых
    0.46
    POSITIVE LOGITS
    an
    0.70
    ان
    0.57
    at
    0.48
    c
    0.47
    ar
    0.47
    。
    0.46
    ك
    0.46
    as
    0.46
    J
    0.46
    ب
    0.43
    Activations Density 0.012%

    No Known Activations