© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2377
    Prev
    Next
    INDEX
    Explanations

    non-English words and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    appreciated
    0.39
    ascin
    0.37
     जिंदाबाद
    0.36
     Heated
    0.36
    hexyl
    0.35
     লইয়া
    0.35
     সংসার
    0.35
    əd
    0.34
    erei
    0.34
    𝙞
    0.34
    POSITIVE LOGITS
     zarządz
    0.43
     contenuto
    0.42
    两种
    0.39
     لوبو
    0.39
     tasarım
    0.38
    ٘
    0.38
    ības
    0.38
    /
    0.37
     gestion
    0.37
     rodzaj
    0.37
    Activations Density 0.000%

    No Known Activations