© 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. 81721
    Prev
    Next
    INDEX
    Explanations

    pleasant surprise

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

    business and private matters

    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
     எல்ல
    0.53
    RIG
    0.48
    了
    0.48
    ਰ
    0.48
    legisl
    0.46
    GUN
    0.46
    LD
    0.45
     बीजेपी
    0.45
    NDA
    0.45
    Religion
    0.45
    POSITIVE LOGITS
     lymph
    0.50
     natives
    0.46
     sms
    0.46
     deh
    0.44
     conduire
    0.44
    ɧ
    0.43
     sáng
    0.43
     orphans
    0.43
     endanger
    0.43
     applicants
    0.42
    Activations Density 0.001%

    No Known Activations