© 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. 59431
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    www

    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
     মানবতার
    0.44
     მიმოწერა
    0.44
    訥
    0.44
     nonresident
    0.42
     Nonprofit
    0.42
    nyder
    0.41
     ましょう
    0.41
    owne
    0.41
     Effective
    0.41
     annualized
    0.41
    POSITIVE LOGITS
    جات
    0.55
     tenemos
    0.53
     seleccion
    0.50
     temos
    0.50
     kis
    0.48
     posso
    0.48
    🥰
    0.47
     selecion
    0.47
    Tenemos
    0.47
     kalian
    0.46
    Activations Density 0.025%

    No Known Activations