© 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. 108353
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    ണു
    0.44
    ไฟฟ้า
    0.44
     Sleep
    0.44
    
    0.43
     All
    0.43
     Hippo
    0.43
     applaud
    0.41
    Mist
    0.41
    Ց
    0.40
     gears
    0.40
    POSITIVE LOGITS
     وزير
    0.48
     retrouvé
    0.45
    تي
    0.44
     retrouver
    0.43
    ܠ
    0.43
    韜
    0.42
     dépassant
    0.42
    دس
    0.42
     decisiones
    0.41
    giène
    0.41
    Activations Density 0.005%

    No Known Activations