© 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. 198379
    Prev
    Next
    INDEX
    Explanations

    legal and sports contexts

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

    AI, Python, fruits

    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
    字节
    0.50
    Ар
    0.49
    Datos
    0.48
    A
    0.48
    atypes
    0.48
    表达式
    0.47
    م
    0.47
    于
    0.46
     Postgres
    0.45
    <unused994>
    0.45
    POSITIVE LOGITS
     litig
    0.55
     trek
    0.48
     traders
    0.48
     trader
    0.47
     litigation
    0.44
     Leagues
    0.44
     decontamination
    0.44
     litigants
    0.43
    感覺
    0.43
     lubrication
    0.42
    Activations Density 0.000%

    No Known Activations