© 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. 2690
    Prev
    Next
    INDEX
    Explanations

    mathematical powers and expressions

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

    The neuron strongly activates on algebraic variable terms—especially occurrences of “x” in math expressions (like “x+3/x–4”).

    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
    ce
    0.66
    oft
    0.66
    might
    0.66
    liked
    0.63
    mystery
    0.63
    c
    0.63
    ceased
    0.63
    crit
    0.62
    culture
    0.61
    scheduled
    0.60
    POSITIVE LOGITS
     $+
    0.76
    ﻄ
    0.76
    +"
    0.76
    +'-
    0.68
    +"|
    0.64
    ২৫
    0.63
    ধু
    0.63
     Atención
    0.63
    ွ
    0.63
    +$
    0.63
    Activations Density 0.000%

    No Known Activations