© 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. 12819
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific symbols

    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
    రెడ్డి
    0.65
    {$\
    0.64
     działania
    0.62
    {}\
    0.61
     facilitar
    0.61
    すすめ
    0.60
    жением
    0.60
     লিখেছেন
    0.60
    {(\
    0.59
     สื
    0.59
    POSITIVE LOGITS
    पर्यंत
    0.61
    েম্ব
    0.53
     radians
    0.50
     pice
    0.50
     flour
    0.49
    gea
    0.49
     radian
    0.49
    ∕
    0.49
     melts
    0.48
    ₁,
    0.48
    Activations Density 0.002%

    No Known Activations