© 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. 783
    Prev
    Next
    INDEX
    Explanations

    language identification

    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
    ING
    0.61
    手
    0.50
    ing
    0.47
    P
    0.45
    谁
    0.43
    けると
    0.43
    I
    0.43
    不行
    0.43
    史
    0.43
    私も
    0.42
    POSITIVE LOGITS
     Zon
    0.45
     ಮುಂದೆ
    0.44
     युवाओ
    0.44
    ci
    0.43
     Tex
    0.43
     Anzahl
    0.43
     Espan
    0.42
    üsse
    0.42
     由
    0.42
     ৮
    0.42
    Activations Density 0.001%

    No Known Activations