© 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. 37444
    Prev
    Next
    INDEX
    Explanations

    business and legal contexts

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

    Neovim configure tailor

    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
     can
    0.49
    扎
    0.49
     Store
    0.46
    藏
    0.46
    or
    0.46
    IP
    0.46
     isn
    0.45
    ao
    0.45
    ocuk
    0.45
     restaurant
    0.45
    POSITIVE LOGITS
     দূত
    0.52
    
    0.51
     Protestants
    0.50
     agricult
    0.50
    бу
    0.50
    法施行令
    0.49
     справо
    0.49
    農
    0.49
    ном
    0.48
     農
    0.48
    Activations Density 0.000%

    No Known Activations