© 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. 144677
    Prev
    Next
    INDEX
    Explanations

    foreign language identification

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

    advocate, ensure, suggest

    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
     vise
    0.46
    嘭
    0.42
    ンスター
    0.42
     Prestige
    0.42
     volunt
    0.41
     stabilit
    0.41
     der
    0.41
     returning
    0.41
     prerequisite
    0.41
     Pronto
    0.41
    POSITIVE LOGITS
    เขา
    0.49
     ሃ
    0.49
    ﺒ
    0.48
    אל
    0.45
    الإنجليزية
    0.45
     máme
    0.43
     shew
    0.42
     אל
    0.42
     접속
    0.41
    ሳሌ
    0.41
    Activations Density 0.002%

    No Known Activations