© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1647
    Prev
    Next
    INDEX
    Explanations

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    它们的
    0.90
    ﺠ
    0.83
    clust
    0.83
    ([^
    0.81
    nbs
    0.80
    ﺮ
    0.80
    debug
    0.79
    blob
    0.78
    $(\
    0.77
    Its
    0.76
    POSITIVE LOGITS
     William
    1.76
     Smith
    1.69
     Robert
    1.68
     Williams
    1.64
     Patrick
    1.62
     Joseph
    1.62
     Andrew
    1.61
     Anthony
    1.61
     Michael
    1.61
     Richard
    1.59
    Activations Density 0.284%

    No Known Activations