© 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. 56786
    Prev
    Next
    INDEX
    Explanations

    explaining limitations or clarifying concepts

    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
    ные
    0.43
    <unused210>
    0.42
     ناقابل
    0.41
     الأمريكية
    0.41
    嶙
    0.41
    ların
    0.40
    RefreshToken
    0.40
     hiểm
    0.40
     treacherous
    0.39
    زش
    0.39
    POSITIVE LOGITS
    ᓗ
    0.40
    🤶
    0.37
     abb
    0.37
     lyrics
    0.37
     trist
    0.37
     배웠
    0.37
     salwar
    0.36
     muziek
    0.36
    listen
    0.35
     With
    0.35
    Activations Density 0.042%

    No Known Activations