© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3835
    Prev
    Next
    INDEX
    Explanations

    border-radius

    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
    거든
    1.54
    蹶
    1.41
    uate
    1.38
    ering
    1.37
    erapeut
    1.37
     defy
    1.37
     rated
    1.36
    ere
    1.32
    eree
    1.31
    omet
    1.31
    POSITIVE LOGITS
     alcun
    1.90
     diferencia
    1.89
     capire
    1.87
    มุม
    1.80
    ت
    1.79
    WindowConstants
    1.78
    ล
    1.77
    ৪১
    1.77
    ప
    1.77
    ২৫
    1.75
    Activations Density 0.014%

    No Known Activations