© 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. 176970
    Prev
    Next
    INDEX
    Explanations

    modern, vintage, storage, thank

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

    no explicit rules

    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
    ѐ
    0.49
    Cone
    0.46
    कार
    0.46
     हू
    0.46
    يديا
    0.46
    Dg
    0.45
     huwa
    0.45
     manners
    0.45
    பூ
    0.45
     refreshments
    0.45
    POSITIVE LOGITS
     Euclidean
    0.47
    고
    0.44
     clin
    0.44
    t
    0.44
     perspect
    0.43
     Fibonacci
    0.43
     euclidean
    0.42
     getDescription
    0.41
     Caucasian
    0.41
     shakespeare
    0.41
    Activations Density 0.001%

    No Known Activations