© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50392
    Prev
    Next
    INDEX
    Explanations

    Hutong or hotline

    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_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
     démontrer
    0.42
    
    0.38
    ᓪ
    0.37
    rated
    0.37
    ハー
    0.37
    व्ही
    0.37
    績
    0.36
    叉
    0.36
    ิต
    0.36
    ন্দ
    0.36
    POSITIVE LOGITS
     underdeveloped
    0.40
    станции
    0.37
     بلوچ
    0.35
    BackPressed
    0.35
     inflated
    0.35
     Manus
    0.35
     kahe
    0.34
    翎
    0.34
    ческая
    0.34
    琊
    0.34
    Activations Density 0.007%

    No Known Activations