© 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. 39550
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    make the or your

    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
     ゼ
    0.43
     ダイヤモンド
    0.42
     buen
    0.42
     poema
    0.41
     フレ
    0.41
    ケーブル
    0.40
     elektromagnet
    0.40
     絶対
    0.40
     CCCC
    0.40
     ക്ര
    0.40
    POSITIVE LOGITS
     योर
    0.46
     времена
    0.43
    越来越多的
    0.43
     चीनी
    0.42
    轺
    0.42
    馊
    0.42
    пень
    0.42
     높아
    0.42
     решение
    0.42
    烫
    0.41
    Activations Density 0.000%

    No Known Activations