© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9189
    Prev
    Next
    INDEX
    Explanations

    list formatting instructions

    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
    cellSize
    0.75
    이고
    0.73
    ћин
    0.67
    였
    0.66
    newToken
    0.65
    하고
    0.62
    IntVar
    0.61
    >,</
    0.61
    ",[(
    0.61
    ，
    0.61
    POSITIVE LOGITS
     This
    1.20
     The
    1.12
     They
    1.09
     There
    1.05
     ٢
    0.97
     We
    0.96
     It
    0.93
     These
    0.91
    This
    0.91
     When
    0.91
    Activations Density 0.395%

    No Known Activations