© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3718
    Prev
    Next
    INDEX
    Explanations

    Volatility, Range, Description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    EntityFramework
    2.05
    ㄹ
    2.02
    omány
    1.83
     comunque
    1.78
    เลี้ยง
    1.77
     उन्ह
    1.76
    ğın
    1.72
     vésicules
    1.71
    镛
    1.70
     Roskov
    1.70
    POSITIVE LOGITS
     На
    1.92
     traders
    1.80
     处理
    1.75
     ‫
    1.70
     Traders
    1.69
    utenants
    1.68
     За
    1.68
     客
    1.68
     Для
    1.65
     nationalists
    1.65
    Activations Density 0.057%

    No Known Activations