© 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. 92195
    Prev
    Next
    INDEX
    Explanations

    foreign languages and nationalities

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

    foreign languages and generalizations

    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
     workings
    0.44
    resolved
    0.44
    рни
    0.43
     (<
    0.43
    ęt
    0.39
    říve
    0.39
    ↵↵
    0.38
    ensington
    0.37
    р
    0.37
     appointed
    0.37
    POSITIVE LOGITS
     испан
    0.56
     kasi
    0.53
    สนามกีฬา
    0.52
     itali
    0.52
     tàu
    0.50
     кора
    0.50
    อังกฤษ
    0.50
     Copa
    0.49
     фильм
    0.49
     spagn
    0.49
    Activations Density 0.000%

    No Known Activations