© 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. 101689
    Prev
    Next
    INDEX
    Explanations

    multi-lingual text features

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

    efficient ways

    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
     refuted
    0.50
    ’
    0.49
     Types
    0.48
     discharged
    0.45
     kth
    0.45
     građ
    0.45
     Scotia
    0.44
     clarified
    0.44
     অভিম
    0.44
     shag
    0.44
    POSITIVE LOGITS
    бот
    0.52
    зму
    0.46
    ס
    0.46
    ות
    0.44
    ны
    0.44
    зу
    0.44
    热情
    0.44
    дары
    0.43
    ëm
    0.43
    ամ
    0.42
    Activations Density 0.001%

    No Known Activations