© 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. 144389
    Prev
    Next
    INDEX
    Explanations

    university business

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

    conservative Legal, momentum, descriptions

    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
     까지
    0.52
    тор
    0.50
     여기가
    0.48
    ะ
    0.48
    ที่เป็น
    0.48
    atorios
    0.46
    ptious
    0.44
    恝
    0.44
    년에
    0.43
    ключа
    0.43
    POSITIVE LOGITS
     gentle
    0.45
     ingeniero
    0.43
     Саша
    0.42
     potvr
    0.41
    ണിക്ക
    0.41
    帶
    0.41
     Colton
    0.39
     AgNO
    0.38
     ions
    0.38
     decenas
    0.38
    Activations Density 0.000%

    No Known Activations