© 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. 186927
    Prev
    Next
    INDEX
    Explanations

    were high

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

    units and specific compounds

    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
    hase
    0.54
    т
    0.49
    getChild
    0.45
    CTED
    0.45
     Arif
    0.44
    তিতে
    0.43
    群众
    0.43
    arrêter
    0.43
    raged
    0.42
    getahuan
    0.42
    POSITIVE LOGITS
     resolutions
    0.48
    ม
    0.45
     sym
    0.45
    4
    0.45
     моей
    0.45
     uranyl
    0.44
     derel
    0.44
     MySQL
    0.44
     prvo
    0.44
    Moj
    0.43
    Activations Density 0.001%

    No Known Activations