© 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. 200158
    Prev
    Next
    INDEX
    Explanations

    dominant architecture

    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
    a
    0.48
    d
    0.47
    u
    0.47
     predicts
    0.46
    y
    0.44
    5
    0.43
    4
    0.43
    kaan
    0.43
    re
    0.42
     holds
    0.42
    POSITIVE LOGITS
     sách
    0.58
     Digestive
    0.49
     FURN
    0.49
     Deutsche
    0.47
    %");
    0.46
    раздо
    0.46
     tibia
    0.46
     sufrir
    0.45
    ského
    0.45
     proporcionan
    0.44
    Activations Density 0.000%

    No Known Activations