© 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. 207195
    Prev
    Next
    INDEX
    Explanations

    code references and pixel values

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

    graphics coordinates and dimensions

    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
    ід
    0.49
    ンドン
    0.49
    ーク
    0.47
    みんな
    0.47
    सलमान
    0.45
    доль
    0.45
    คน
    0.44
    ᐢ
    0.44
    PLACES
    0.44
    場所
    0.44
    POSITIVE LOGITS
    ;
    0.47
     onwards
    0.44
     chảy
    0.41
    ↵
    0.41
     torna
    0.41
     skillet
    0.40
     bouton
    0.40
     买
    0.40
     asm
    0.39
     venture
    0.39
    Activations Density 0.000%

    No Known Activations