© 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. 169723
    Prev
    Next
    INDEX
    Explanations

    farm closures, since, harmful, tournaments, shop, song, organ, delicious

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

    offering help if you

    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
    L
    0.54
    די
    0.53
     Statewide
    0.51
    ↵
    0.49
    m
    0.49
    du
    0.49
    de
    0.48
     statewide
    0.48
    太
    0.48
    G
    0.47
    POSITIVE LOGITS
     ними
    0.56
     импе
    0.55
     कार्यकर्
    0.52
     núcle
    0.50
     фев
    0.50
     lesquels
    0.50
     extrema
    0.49
    шенко
    0.48
     мони
    0.47
     август
    0.47
    Activations Density 0.000%

    No Known Activations