© 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. 110093
    Prev
    Next
    INDEX
    Explanations

    public transportation

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

    distribution, competitive, consistent

    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
    Not in Any Lists

    No Comments

    Negative Logits
    শ
    0.51
    ন
    0.49
     Kant
    0.48
    澫
    0.45
    อิน
    0.45
    ნი
    0.45
    Dij
    0.44
    د
    0.43
    ил
    0.43
    madan
    0.43
    POSITIVE LOGITS
     °
    0.52
     remark
    0.52
     folks
    0.50
     hostname
    0.49
    gggg
    0.48
     pictogram
    0.47
     patients
    0.46
     hostess
    0.46
     militia
    0.44
     simulate
    0.44
    Activations Density 0.000%

    No Known Activations