© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 244949
    Prev
    Next
    INDEX
    Explanations

    locations, events, time

    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
     autorización
    0.50
     امور
    0.49
    ক
    0.48
     múltipl
    0.46
    მ
    0.46
     múltiples
    0.45
    屡
    0.45
     עם
    0.45
    マルチ
    0.44
    人了
    0.44
    POSITIVE LOGITS
     যাহা
    0.49
     food
    0.47
     previous
    0.47
     ride
    0.47
     downg
    0.46
     drinking
    0.46
    FED
    0.45
    ud
    0.45
     boosting
    0.45
     houses
    0.45
    Activations Density 0.000%

    No Known Activations