© 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. 87403
    Prev
    Next
    INDEX
    Explanations

    lists phrases and terms

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

    proprietary, term, delving, encoder, Manager, Lost

    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
    на
    0.61
    וי
    0.53
    ко
    0.52
    ય
    0.52
    Пі
    0.52
    나
    0.51
    פ
    0.50
    warning
    0.49
    ТО
    0.49
    BLUE
    0.49
    POSITIVE LOGITS
     Michigan
    0.54
     Maserati
    0.53
     Caramel
    0.52
     Metric
    0.51
     Giv
    0.50
     aquifer
    0.48
     Chi
    0.47
     artery
    0.47
     Minnesota
    0.47
     ™
    0.47
    Activations Density 0.001%

    No Known Activations