© 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. 56254
    Prev
    Next
    INDEX
    Explanations

    was uploaded, they have, and non

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

    adjustments needed for part-time

    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
    負
    0.50
    明確
    0.46
    創
    0.46
    原則
    0.46
    ങ്ങളില്‍
    0.45
    ଲେ
    0.45
    確
    0.45
    耂
    0.45
    醯
    0.44
    抹茶
    0.43
    POSITIVE LOGITS
     çıkart
    0.54
     indir
    0.48
     בה
    0.46
     interni
    0.46
     victoire
    0.44
     оці
    0.44
     তাহারা
    0.44
     editar
    0.44
     successo
    0.43
    isierung
    0.43
    Activations Density 0.000%

    No Known Activations