© 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. 85285
    Prev
    Next
    INDEX
    Explanations

    crore belonging, cup of, match in

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

    error types?

    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
     fugitive
    0.44
     रूसी
    0.40
    娓
    0.39
     Fahrt
    0.37
    福岡
    0.37
     Vorstand
    0.36
    मर्श
    0.36
     Albion
    0.36
     biliary
    0.36
    私募基金
    0.36
    POSITIVE LOGITS
    6
    0.45
    ^{
    0.45
    0
    0.45
    9
    0.45
    2
    0.45
    4
    0.44
    ゜
    0.44
    1
    0.44
    7
    0.44
    NUMX
    0.43
    Activations Density 0.349%

    No Known Activations