© 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. 17092
    Prev
    Next
    INDEX
    Explanations

    for loops and resources

    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
    in
    1.30
    I
    0.79
    O
    0.73
    S
    0.68
    es
    0.67
    al
    0.67
    oč
    0.67
    o
    0.66
    ewöhn
    0.66
    ed
    0.65
    POSITIVE LOGITS
     sake
    0.75
    geries
    0.72
     naught
    0.62
     purposes
    0.59
     रवाना
    0.57
     instance
    0.55
    giveness
    0.55
    asmuch
    0.53
     unterwegs
    0.53
    ку
    0.52
    Activations Density 0.040%

    No Known Activations