© 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. 80858
    Prev
    Next
    INDEX
    Explanations

    multi-lingual characters

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

    U: followed by colon

    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
     despot
    0.44
    Fat
    0.42
     δικ
    0.42
    quit
    0.40
    vers
    0.39
     terror
    0.39
    FAT
    0.39
    積
    0.39
    ↵↵↵
    0.39
    Lose
    0.39
    POSITIVE LOGITS
     Nachricht
    0.47
    നുള്ള
    0.46
    のデザイン
    0.46
     modèles
    0.45
     костю
    0.45
    สำหรับ
    0.44
     spéc
    0.44
     puisse
    0.44
    icky
    0.43
     alimentaires
    0.43
    Activations Density 0.000%

    No Known Activations