© 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. 103716
    Prev
    Next
    INDEX
    Explanations

    water, sewer, utilities

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

    arguments, bee, sheriff, against

    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
    pyx
    0.52
    ျ
    0.44
    contact
    0.44
    explain
    0.44
    in
    0.43
    extract
    0.43
    pageX
    0.43
    at
    0.43
    เลข
    0.43
     Tree
    0.43
    POSITIVE LOGITS
    ého
    0.50
     रजिस्ट्रेशन
    0.49
    ྥ
    0.47
     quenching
    0.46
     ރ
    0.46
     incidences
    0.45
     abdom
    0.45
    üyük
    0.45
     steaks
    0.45
     kože
    0.44
    Activations Density 0.001%

    No Known Activations