© 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. 107686
    Prev
    Next
    INDEX
    Explanations

    services and quantities

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

    explanation of

    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
     the
    0.58
    the
    0.51
    quis
    0.50
    题目
    0.48
     boarded
    0.46
    ,
    0.46
     a
    0.46
    有
    0.46
    দে
    0.46
    ï
    0.46
    POSITIVE LOGITS
    hatiti
    0.54
     커피
    0.52
     petani
    0.49
     காற்றின்
    0.49
    ertung
    0.47
     mlijeka
    0.47
    aży
    0.46
     দিনাজ
    0.46
     कॉफी
    0.45
     agricole
    0.45
    Activations Density 0.000%

    No Known Activations