© 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. 3705
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    യും
    0.55
     déclar
    0.55
     DELHI
    0.54
    ן
    0.53
    ‥
    0.52
     più
    0.52
     Boliv
    0.52
     Matteo
    0.51
     ہُ
    0.51
     bygg
    0.51
    POSITIVE LOGITS
    o
    0.65
    ad
    0.53
    {
    0.52
    in
    0.52
    v
    0.48
    as
    0.47
    over
    0.47
     Sequences
    0.47
    distance
    0.46
    dist
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.