© 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. 1645
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
    penas
    0.34
     resalt
    0.33
     Lastly
    0.32
    网上
    0.32
    惆
    0.32
     Disclaimer
    0.32
    还有一个
    0.32
     Change
    0.32
     Find
    0.31
     Check
    0.31
    POSITIVE LOGITS
     studs
    0.30
     epidemi
    0.30
    ীব
    0.29
    ضا
    0.28
    ชน์
    0.28
    δ
    0.28
     activism
    0.28
     epidermis
    0.27
     fellowships
    0.27
     poles
    0.27
    Activations Density 0.094%

    No Known Activations