© 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. 199046
    Prev
    Next
    INDEX
    Explanations

    analyzing usage of data

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

    figure, current, VR, prices

    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
    บล
    0.42
    Born
    0.40
    юще
    0.40
     bords
    0.39
    得
    0.39
     olnud
    0.38
    支持
    0.38
    ยาน
    0.38
     yd
    0.38
     hjel
    0.37
    POSITIVE LOGITS
     પોતાના
    0.56
     પોતાની
    0.54
     ແ
    0.53
    rparam
    0.52
     அற்புதமான
    0.51
     Schwar
    0.50
     કર્યું
    0.50
     चन्द्र
    0.48
     પોતા
    0.48
     போரா
    0.48
    Activations Density 0.000%

    No Known Activations