© 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. 142843
    Prev
    Next
    INDEX
    Explanations

    words preceding numbers

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

    subrogation, role, communication, wind energy

    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
     sorprendente
    0.59
     rapp
    0.50
    ۱۹
    0.44
    சில்
    0.44
     //[
    0.44
     Griffiths
    0.44
    റിയ
    0.43
     विवे
    0.43
     Metallica
    0.43
     musicians
    0.43
    POSITIVE LOGITS
    ের
    0.52
    s
    0.49
    ی
    0.46
    ਆਂ
    0.46
     údaje
    0.45
    washing
    0.45
    lighet
    0.45
     পাওয়ার
    0.44
     формы
    0.43
    IES
    0.43
    Activations Density 0.000%

    No Known Activations