© 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. 3467
    Prev
    Next
    INDEX
    Explanations

    arithmetic subtraction expressions

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

    The neuron is specialized in detecting numerical tokens, especially floating-point numbers with decimal points.

    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
    <0xF1>
    0.57
    נדה
    0.57
    екст
    0.53
     técn
    0.52
    ={$
    0.52
     rusak
    0.52
    তেন
    0.51
     violated
    0.51
     defied
    0.50
    toMatch
    0.49
    POSITIVE LOGITS
     ఎక్కువగా
    0.78
     -(
    0.72
     minus
    0.71
    subtract
    0.71
     ఎక్కువ
    0.70
     Subtract
    0.68
    -(
    0.67
     subtracting
    0.66
     കൂടുത
    0.66
     -
    0.65
    Activations Density 0.001%

    No Known Activations