© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1699
    Prev
    Next
    INDEX
    Explanations

    quantities of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    تاریخ
    0.78
     політи
    0.73
     соціа
    0.69
     justement
    0.68
     aziende
    0.66
    LGBT
    0.66
    SOCIAL
    0.66
    ֜
    0.65
     જાહેર
    0.65
    History
    0.64
    POSITIVE LOGITS
     would
    0.76
     kilograms
    0.71
     could
    0.68
     total
    0.68
     amount
    0.68
     maximum
    0.64
     ounces
    0.64
     centimeters
    0.63
     amounts
    0.61
     maxillary
    0.61
    Activations Density 0.006%

    No Known Activations