© 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. 198711
    Prev
    Next
    INDEX
    Explanations

    recital, Spain, update

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

    multilingual terms and concepts

    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
    审
    0.47
    شو
    0.47
    _
    0.46
    一项
    0.45
    产生的
    0.45
    ون
    0.44
    之人
    0.44
     OPER
    0.44
    opre
    0.43
    ου
    0.43
    POSITIVE LOGITS
     natthi
    0.53
     महे
    0.50
     ܠ
    0.49
     уен
    0.49
    glicherweise
    0.49
     ನ
    0.49
     ممالک
    0.47
    RH
    0.47
     エネルギー
    0.47
     শিল্পের
    0.47
    Activations Density 0.000%

    No Known Activations