© 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. 197688
    Prev
    Next
    INDEX
    Explanations

    money, wrong, 2, on topic, award nomination, orders, call

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

    avoiding moderation

    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
    ana
    0.56
     オー
    0.52
    Mr
    0.52
    FirstName
    0.50
    B
    0.50
    Y
    0.50
    University
    0.48
    Mrs
    0.47
    Life
    0.47
     ymp
    0.47
    POSITIVE LOGITS
     bestow
    0.49
    눕
    0.49
     laminate
    0.48
     достат
    0.46
    лекса
    0.46
     locust
    0.45
     synaptic
    0.44
     retort
    0.43
     disposer
    0.43
     diarrhea
    0.43
    Activations Density 0.001%

    No Known Activations