© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2543
    Prev
    Next
    INDEX
    Explanations

    November dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    鲞
    0.70
     সংখ্যা
    0.70
    ቷ
    0.69
     उषा
    0.68
     ปุ่ม
    0.67
    Კ
    0.67
    各类
    0.67
     રાશિફળ
    0.65
    /***
    0.64
    🔍
    0.64
    POSITIVE LOGITS
     ninth
    0.99
     sixteenth
    0.97
     seventh
    0.95
     fifth
    0.94
     sixth
    0.94
     fifteenth
    0.93
     thirteenth
    0.92
     fourteenth
    0.92
     cinqui
    0.91
     twelfth
    0.90
    Activations Density 0.045%

    No Known Activations