© 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. 33772
    Prev
    Next
    INDEX
    Explanations

    sales and research

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

    lsl scripting context

    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
     দফ
    0.45
     espèces
    0.40
     privata
    0.39
    彤
    0.39
     எனவே
    0.39
     artística
    0.39
     chức
    0.39
    Interactor
    0.39
    摶
    0.39
    インチ
    0.38
    POSITIVE LOGITS
     Seller
    0.45
     Dental
    0.45
     Linton
    0.44
     Buyer
    0.41
     Sellers
    0.41
     Beach
    0.40
     amusing
    0.40
     Sales
    0.40
     research
    0.40
     Fl
    0.40
    Activations Density 0.021%

    No Known Activations