© 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. 41707
    Prev
    Next
    INDEX
    Explanations

    parentheses and code structures

    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
    LeftSide
    0.41
    achos
    0.41
     Roosevelt
    0.40
     крупные
    0.40
     RESP
    0.38
    蓉
    0.38
    Tabpage
    0.38
    Ro
    0.38
     ಹೆ
    0.38
    Electro
    0.37
    POSITIVE LOGITS
    bagai
    0.40
     छुटकारा
    0.39
     हटा
    0.39
    வ்
    0.38
    永远
    0.36
    烁
    0.36
    鳎
    0.35
    更加
    0.35
    ورٹی
    0.35
     rež
    0.34
    Activations Density 0.002%

    No Known Activations