© 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. 5807
    Prev
    Next
    INDEX
    Explanations

    math equations and symbols

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens (numbers, numeric expressions, and related punctuation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     \
    0.63
     nonzero
    0.61
    \
    0.60
     \{\
    0.59
     iterate
    0.59
     notation
    0.58
    using
    0.58
     (\
    0.58
    import
    0.56
    notation
    0.56
    POSITIVE LOGITS
     Дет
    0.60
     బ్యాం
    0.58
     muzy
    0.55
     záb
    0.55
     Центра
    0.55
     청
    0.55
     센터
    0.54
     Многие
    0.54
     Waterfront
    0.54
    เพลง
    0.54
    Activations Density 0.007%

    No Known Activations