© 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. 108803
    Prev
    Next
    INDEX
    Explanations

    issueseffectsrisks

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

    classic riddles or jokes

    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
    manuel
    0.50
    openList
    0.49
    ону
    0.48
     предвари
    0.46
    addressed
    0.44
    baj
    0.44
    獐
    0.44
     ממ
    0.44
    astu
    0.44
     предприятия
    0.43
    POSITIVE LOGITS
     lakes
    0.55
     shap
    0.52
     airplanes
    0.48
     capitalizing
    0.47
     zooms
    0.47
     roc
    0.47
     capturing
    0.46
     dict
    0.46
     beers
    0.46
     technique
    0.46
    Activations Density 0.000%

    No Known Activations