© 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. 20214
    Prev
    Next
    INDEX
    Explanations

    IRC mice, TICA.org, Tic-Tac-Toe, Picnic

    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
     americ
    0.77
    า
    0.75
    ות
    0.68
    と考えて
    0.66
     aastal
    0.66
     assumptive
    0.66
     הראש
    0.65
     espes
    0.65
    รายงาน
    0.64
     carbur
    0.64
    POSITIVE LOGITS
    t
    0.84
     on
    0.82
    c
    0.71
    ني
    0.70
    ри
    0.70
    order
    0.68
    poetrycommunity
    0.68
    os
    0.67
    b
    0.67
    ك
    0.66
    Activations Density 1.072%

    No Known Activations