© 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. 113962
    Prev
    Next
    INDEX
    Explanations

    MPHW jobs, family living

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

    prevent disputes or harmful words

    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
     现在
    0.52
    acterial
    0.51
     Kü
    0.46
    obbly
    0.46
    hta
    0.46
     परेशानी
    0.45
    šli
    0.45
    .
    0.44
    uru
    0.44
     transfection
    0.44
    POSITIVE LOGITS
     дел
    0.52
    ᱭ
    0.50
    ین
    0.49
     особенности
    0.48
    ਮ
    0.47
    ционное
    0.47
    ⏤
    0.46
    ཁ
    0.46
     особенностей
    0.44
    少なくとも
    0.44
    Activations Density 0.000%

    No Known Activations