© 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. 186788
    Prev
    Next
    INDEX
    Explanations

    direct mail

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

    primarily

    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
    ༤
    0.50
    api
    0.48
    oriented
    0.48
    ً
    0.46
    southeast
    0.45
    id
    0.45
    ess
    0.44
     or
    0.44
    rooms
    0.44
    ”]
    0.43
    POSITIVE LOGITS
     Cheetah
    0.47
     Aufbau
    0.47
    PopupWindow
    0.46
    吉
    0.46
    जेट
    0.44
     ሃ
    0.44
     heav
    0.44
     オーバー
    0.44
     gxh
    0.43
    HEIM
    0.43
    Activations Density 0.001%

    No Known Activations