© 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. 40189
    Prev
    Next
    INDEX
    Explanations

    cost or effort

    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
    0.61
     น่า
    0.47
     legume
    0.46
     tuoi
    0.46
    你需要
    0.45
     Нужно
    0.44
     (
    0.43
    [
    0.42
     is
    0.42
     Himalayan
    0.42
    POSITIVE LOGITS
    侙
    0.46
    Ꮺ
    0.44
    стями
    0.44
     pdelay
    0.43
    愭
    0.43
    менить
    0.42
     Förder
    0.42
    ﺔ
    0.42
    沄
    0.42
    лее
    0.41
    Activations Density 0.010%

    No Known Activations