© 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. 32449
    Prev
    Next
    INDEX
    Explanations

    valuation, contract, family, blogs, removal, limit

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

    brand names and specific entities

    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
    同樣
    0.50
    同时
    0.46
    من
    0.46
    و
    0.46
    ❇
    0.43
    lassical
    0.43
    樞
    0.43
    😼
    0.43
    的影响
    0.43
    seva
    0.42
    POSITIVE LOGITS
     Airbus
    0.64
     Cadillac
    0.63
     VW
    0.57
     автомобиль
    0.55
     Yelp
    0.55
     Airbnb
    0.55
     estimator
    0.52
     Ambul
    0.52
     AutoCAD
    0.52
     BEEN
    0.51
    Activations Density 0.000%

    No Known Activations