© 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. 210361
    Prev
    Next
    INDEX
    Explanations

    you have

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

    train models

    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
    ایک
    0.58
    〠
    0.51
     सुद्धा
    0.47
    وف
    0.46
    ونو
    0.45
    あ
    0.45
    িত্যক্ত
    0.45
    敢
    0.44
    simplified
    0.44
     رسید
    0.44
    POSITIVE LOGITS
    ieres
    0.49
     ně
    0.48
    /
    0.48
     *=
    0.48
     catheters
    0.46
     CAT
    0.45
     chips
    0.45
     trail
    0.45
    iet
    0.44
     gering
    0.44
    Activations Density 0.001%

    No Known Activations