© 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. 65991
    Prev
    Next
    INDEX
    Explanations

    national sporting

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

    What is? where?

    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
     brother
    0.48
    ंजी
    0.47
     derrot
    0.46
     escond
    0.46
     dereg
    0.46
     deregulation
    0.46
    T
    0.46
    Ts
    0.45
     processed
    0.45
    TP
    0.45
    POSITIVE LOGITS
    好多
    0.50
     قان
    0.49
    棱
    0.48
     Plugging
    0.48
    zuoye
    0.48
    塑料
    0.47
    ⇅
    0.47
    ♘
    0.46
    ✷
    0.46
    浙
    0.46
    Activations Density 0.000%

    No Known Activations