© 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. 170645
    Prev
    Next
    INDEX
    Explanations

    store, performance, waste, Pixel, tapes, DWI

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

    ancient Greek Hebrew languages

    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
    婹
    0.51
    椛
    0.49
    զ
    0.48
     evolving
    0.47
     programu
    0.46
    cki
    0.45
    arima
    0.45
    ᱩ
    0.45
     Reddy
    0.45
    棤
    0.45
    POSITIVE LOGITS
    Nation
    0.55
    Teacher
    0.51
    Top
    0.50
    Publications
    0.49
    Neigh
    0.48
    All
    0.48
    Pool
    0.48
    Rows
    0.47
    Sites
    0.47
    Types
    0.46
    Activations Density 0.000%

    No Known Activations