© 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. 229748
    Prev
    Next
    INDEX
    Explanations

    moving beyond

    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
    holomorphic
    0.67
    า
    0.58
     recursive
    0.56
    溶液
    0.55
    recursive
    0.54
     옳은
    0.52
     etiology
    0.51
    acic
    0.50
     carcinogenesis
    0.50
    ੇ
    0.50
    POSITIVE LOGITS
     Infrastructure
    0.65
     Maestro
    0.63
     Hippo
    0.63
     Vegas
    0.63
     Realtor
    0.63
     Pueblo
    0.61
     Aloha
    0.61
     Durango
    0.61
     Soho
    0.60
     Eco
    0.60
    Activations Density 0.000%

    No Known Activations