© 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. 248338
    Prev
    Next
    INDEX
    Explanations

    non-english and punctuation

    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
    nders
    0.49
    cars
    0.44
    ющем
    0.43
    isset
    0.42
    gn
    0.41
    controllers
    0.41
    GUND
    0.41
    丑
    0.41
    casters
    0.41
     stagnant
    0.41
    POSITIVE LOGITS
     เฉล
    0.61
    dimethyl
    0.54
     正規
    0.52
     サングラス
    0.52
     സൂര്യ
    0.51
     ആവശ്യ
    0.50
     دیتے
    0.50
    と呼ばれる
    0.49
     Вайлдберриз
    0.49
     routinely
    0.49
    Activations Density 0.000%

    No Known Activations