© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4390
    Prev
    Next
    INDEX
    Explanations

    industry and business

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    BURG
    2.03
    ···
    1.75
    城市的
    1.73
    〠
    1.70
    CITY
    1.67
    ····
    1.67
     CITY
    1.65
    umsi
    1.65
    邑
    1.64
    acterial
    1.62
    POSITIVE LOGITS
     Bets
    1.13
    фессиона
    1.07
     جائز
    0.99
     требованиям
    0.97
     Efforts
    0.95
    عان
    0.95
    Боль
    0.93
     Mev
    0.90
     Fus
    0.90
     Awards
    0.89
    Activations Density 0.066%

    No Known Activations