© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11185
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations and calculations

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

    The main thing this neuron does is identify numeric tokens in arithmetic or date‐calculation expressions.

    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
    ℤ
    0.61
    pm
    0.61
    affine
    0.60
    g
    0.59
    t
    0.56
    г
    0.56
    gp
    0.56
    sh
    0.55
    c
    0.55
    Если
    0.55
    POSITIVE LOGITS
     freelancers
    0.70
     lieutenant
    0.70
     VLAN
    0.67
     purchasers
    0.65
     servicemen
    0.64
     saltwater
    0.64
     ナイス
    0.63
     resellers
    0.63
     profesionales
    0.63
     asesor
    0.63
    Activations Density 0.001%

    No Known Activations