© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117880
    Prev
    Next
    INDEX
    Explanations

    characters or domain names

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

    investigate further or phase

    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
    Negative Logits
     الاشتراك
    0.51
     গলা
    0.48
    CONH
    0.48
     MARC
    0.47
     గ్రా
    0.46
    UNITY
    0.45
    ModelComponent
    0.45
     パール
    0.45
     Hager
    0.44
     ਭ
    0.43
    POSITIVE LOGITS
    文
    0.51
    城
    0.47
     yine
    0.46
    开
    0.46
    ﭥ
    0.45
    minin
    0.44
    ta
    0.44
    Encoding
    0.44
    toires
    0.42
    اؤ
    0.42
    Activations Density 0.000%

    No Known Activations