© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8839
    Prev
    Next
    INDEX
    Explanations

    Thank you

    np_acts-logits-general · gemini-2.5-flash-lite

    access personalized features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ्स
    0.52
    ाय
    0.51
     sturdy
    0.46
    ヒ
    0.46
    Options
    0.43
    bodyParser
    0.43
    ज
    0.43
    ிக
    0.43
     अफ्रीका
    0.43
    ਜ
    0.42
    POSITIVE LOGITS
     الجرس
    0.53
     這
    0.52
     شكله
    0.51
     Mutations
    0.51
     té
    0.50
     計
    0.50
     คํา
    0.50
     計算
    0.49
     ดิ
    0.49
     هناك
    0.49
    Activations Density 0.000%

    No Known Activations