© 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. 107995
    Prev
    Next
    INDEX
    Explanations

    multilingual terms

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

    Russian, Spanish, French, Hebrew, Sanskrit

    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
     fertil
    0.45
    აქ
    0.45
    تن
    0.45
     tato
    0.45
    ї
    0.44
    تم
    0.44
    تور
    0.43
    耕
    0.43
    .
    0.43
    ميل
    0.43
    POSITIVE LOGITS
     также
    0.53
     таксама
    0.50
     triple
    0.49
    Triple
    0.49
     Triple
    0.49
    enaire
    0.48
     коми
    0.48
    nagar
    0.48
    ripciones
    0.47
     пакет
    0.47
    Activations Density 0.001%

    No Known Activations