© 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. 249668
    Prev
    Next
    INDEX
    Explanations

    words across languages

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Cra
    0.48
    "]').
    0.48
    school
    0.48
    HPO
    0.45
    Cra
    0.45
    ボ
    0.44
     mathematician
    0.44
    number
    0.43
    nutrition
    0.43
     Poppy
    0.43
    POSITIVE LOGITS
     نتيجة
    0.52
    compId
    0.48
     llegará
    0.46
     arrivée
    0.45
    绡
    0.45
     컴
    0.45
    iseaux
    0.44
     sealed
    0.44
     由于
    0.44
     confining
    0.44
    Activations Density 0.000%

    No Known Activations