© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31921
    Prev
    Next
    INDEX
    Explanations

    Continuous section breaks

    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_40_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
    etchup
    0.46
    ewidth
    0.42
    テール
    0.39
    薄
    0.38
     පුද්ග
    0.38
    plicate
    0.37
     widths
    0.36
    ",{
    0.36
    پوینت
    0.36
    之内
    0.36
    POSITIVE LOGITS
     CNC
    0.45
    FAQs
    0.43
     Subsidi
    0.41
    CNC
    0.40
     still
    0.40
     CNT
    0.39
    вые
    0.39
    still
    0.39
    зме
    0.39
      
    0.38
    Activations Density 0.000%

    No Known Activations