© 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. 168470
    Prev
    Next
    INDEX
    Explanations

    know from, continuously improve, 've been, State of

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

    serve different functions

    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
    画
    0.50
    在
    0.49
    好
    0.49
    第
    0.45
    一开始
    0.44
    lime
    0.43
    (
    0.42
    学
    0.42
     creativity
    0.42
    越
    0.42
    POSITIVE LOGITS
     ダイヤモンド
    0.56
     जाईल
    0.54
     ಸಂಸ್ಥ
    0.52
     څرنګوالی
    0.50
     अड्डा
    0.50
    <unused22>
    0.50
     ቦ
    0.50
     お知らせ
    0.50
     那麼
    0.49
     diing
    0.49
    Activations Density 0.000%

    No Known Activations