© 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. 192892
    Prev
    Next
    INDEX
    Explanations

    English, other languages, and punctuation

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

    explaining questions

    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
    ist
    0.54
    ותר
    0.48
     تاک
    0.47
    ojas
    0.47
    iefer
    0.47
     सांस
    0.47
    adda
    0.46
    轫
    0.46
     Mohr
    0.46
     기울
    0.46
    POSITIVE LOGITS
     hats
    0.49
     kag
    0.47
    بت
    0.47
    σκο
    0.46
    тки
    0.45
    槍
    0.45
     funcionamento
    0.44
    Natalie
    0.44
    дко
    0.44
    дни
    0.44
    Activations Density 0.001%

    No Known Activations