© 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. 2983
    Prev
    Next
    INDEX
    Explanations

    USB drive, port, or debugging

    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
    :‏
    2.91
    lineContainer
    2.85
    伀
    2.76
    triggered
    2.75
    ʡ
    2.75
    getRadius
    2.67
    िल्‍ली
    2.65
    liner
    2.62
    
    2.62
    뿯
    2.57
    POSITIVE LOGITS
    weds
    2.30
    மிய
    2.23
    ++);
    2.11
    akukannya
    2.11
    द
    2.09
     څه
    2.07
    ++)
    2.06
    alek
    2.04
     vars
    2.03
    ford
    2.00
    Activations Density 0.012%

    No Known Activations