© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3007
    Prev
    Next
    INDEX
    Explanations

    Python class initialization

    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_31_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
     koul
    0.64
     {})
    0.61
     Were
    0.61
     nl
    0.60
     sist
    0.59
     Nope
    0.57
     syukur
    0.56
     Indeed
    0.55
     düş
    0.55
     Falling
    0.55
    POSITIVE LOGITS
    initWith
    0.77
    pars
    0.67
    self
    0.66
    __(
    0.65
    parser
    0.61
    ି
    0.61
    initializer
    0.61
    пар
    0.61
    digest
    0.60
    pageControl
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.