© 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. 103546
    Prev
    Next
    INDEX
    Explanations

    invite you to join

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

    sometimes help

    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
     and
    0.57
     diplomatic
    0.51
     garment
    0.46
     for
    0.46
     Italian
    0.46
     Api
    0.46
     capability
    0.45
    .
    0.45
    ⠿
    0.44
    api
    0.44
    POSITIVE LOGITS
    Nast
    0.52
    entionally
    0.50
    Poz
    0.48
    Lawrence
    0.47
     விகி
    0.47
    děpodob
    0.47
    Hfn
    0.47
    DCTask
    0.47
     نسبة
    0.47
     počet
    0.46
    Activations Density 0.001%

    No Known Activations