© 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. 167959
    Prev
    Next
    INDEX
    Explanations

    language tokens and special characters

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

    convert a string, mistake, noir, squares, ization

    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
     ZIP
    0.42
    '});
    0.41
     mask
    0.40
     Palabra
    0.40
    Word
    0.40
    াই
    0.39
    周知
    0.39
     hulle
    0.39
    Artikel
    0.38
    燒
    0.38
    POSITIVE LOGITS
    .@
    0.54
    ὃ
    0.54
     overland
    0.52
    장은
    0.51
     어떻게
    0.50
    인이
    0.50
     소녀
    0.50
    into
    0.49
    onder
    0.48
    도로
    0.48
    Activations Density 0.000%

    No Known Activations