© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10935
    Prev
    Next
    INDEX
    Explanations

    equation variables and symbols

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

    The neuron strongly activates on single‐letter or short alphanumeric tokens used as mathematical variables or parameters in formulas.

    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
    )^{
    0.78
    )^{\
    0.75
    )+\
    0.72
    }+\
    0.69
    )^{(
    0.68
     \
    0.66
    )_{\
    0.65
    +\
    0.64
    )+
    0.63
    ^{\
    0.63
    POSITIVE LOGITS
     marchio
    0.68
     tenere
    0.63
     prerog
    0.61
     riguard
    0.60
     danza
    0.59
     vigilancia
    0.59
     достой
    0.59
     religiosos
    0.59
     salespeople
    0.59
     dando
    0.59
    Activations Density 0.016%

    No Known Activations