© 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. 94309
    Prev
    Next
    INDEX
    Explanations

    citizen participation

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

    Area or wide area network

    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
     haven
    0.51
     dejo
    0.48
     didn
    0.46
    ٻ
    0.46
     hasn
    0.45
     panas
    0.44
     reichen
    0.44
     doesn
    0.43
     dejan
    0.43
     lessen
    0.42
    POSITIVE LOGITS
     यूनिवर्सल
    0.48
     मॉडलिंग
    0.47
     其中
    0.45
    álni
    0.44
     মুদ্রিত
    0.44
    typography
    0.44
    钾
    0.44
     topographic
    0.43
     ką
    0.43
     फोटोशूट
    0.43
    Activations Density 0.001%

    No Known Activations