© 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. 56611
    Prev
    Next
    INDEX
    Explanations

    force on or in

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

    allowed values are

    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
    主人
    0.56
    circledR
    0.52
    čnom
    0.52
     தேர்தல்
    0.51
     призна
    0.50
     задержа
    0.49
    吾
    0.49
    峩
    0.49
    ご了承
    0.48
     עד
    0.48
    POSITIVE LOGITS
     spider
    0.47
     odl
    0.46
     pp
    0.44
     Transformer
    0.44
     Hello
    0.44
     rocket
    0.44
     aba
    0.43
    رب
    0.43
    ودي
    0.42
     Haskell
    0.42
    Activations Density 0.000%

    No Known Activations