© 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. 36841
    Prev
    Next
    INDEX
    Explanations

    license usage

    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
    껐
    0.37
    扱
    0.37
    潔
    0.36
    ษา
    0.36
     unquestion
    0.35
     निम्न
    0.35
    描き
    0.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.34
     クリア
    0.34
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.34
    POSITIVE LOGITS
    ж
    0.41
    ពិស
    0.39
     ঝ
    0.38
    ⎞
    0.38
     Popular
    0.38
     TOP
    0.38
    cparam
    0.38
    CharPtr
    0.38
     I
    0.37
     Fancy
    0.37
    Activations Density 0.019%

    No Known Activations