© 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. 167872
    Prev
    Next
    INDEX
    Explanations

    slow down or leave out

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

    quantities and specifications

    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
    Bibliografia
    0.51
     enzimas
    0.48
     наслед
    0.47
     мастера
    0.45
     задачи
    0.44
    出错
    0.43
    鿢
    0.42
    鍮
    0.42
     ശക്ത
    0.42
     শ্রমিক
    0.41
    POSITIVE LOGITS
     স্বল্প
    0.49
     sogenannten
    0.46
    的一种
    0.45
     invit
    0.44
    olgens
    0.43
     spéciaux
    0.43
    .
    0.42
    ered
    0.42
     sogenannte
    0.42
     contactless
    0.42
    Activations Density 0.001%

    No Known Activations