© 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. 24-GEMMASCOPE-2-RES-16K
    7. 714
    Prev
    Next
    INDEX
    Explanations

    variables and mathematical notation

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

    This neuron fires on single‐letter technical identifiers (e.g. variable names like P, p, q, h, A, B, Γ, Ui) in mathematical or pseudocode contexts.

    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_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
     sosyal
    0.66
     উৎসাহিত
    0.63
     kwiet
    0.61
    criar
    0.59
     otros
    0.58
     другие
    0.58
     başladı
    0.58
    "});
    0.57
    ผิด
    0.57
    Демо
    0.57
    POSITIVE LOGITS
    ∈
    0.71
     ∈
    0.69
     thermodynam
    0.66
     morphologies
    0.64
     polynomials
    0.61
    =$\
    0.60
     (=
    0.59
    <sub>
    0.59
     topologies
    0.59
     such
    0.57
    Activations Density 0.036%

    No Known Activations