© 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. 10567
    Prev
    Next
    INDEX
    Explanations

    Print the

    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
    nin
    1.81
    r
    1.78
    ly
    1.68
    t
    1.61
    mation
    1.57
    i
    1.56
     the
    1.47
    ments
    1.47
    manship
    1.44
    st
    1.44
    POSITIVE LOGITS
     cây
    2.14
    encodeWith
    1.95
     kó
    1.91
    webElementXpaths
    1.91
    ScriptAssemblies
    1.88
     cosidd
    1.85
    <unused1308>
    1.85
    <unused36>
    1.83
    <unused1557>
    1.83
    inheritDoc
    1.82
    Activations Density 0.035%

    No Known Activations