© 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. 762
    Prev
    Next
    INDEX
    Explanations

    over [number] times

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

    This neuron fires on numeric tokens—especially multi-digit numbers and decimal values.

    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
    '
    0.70
    preventDefault
    0.66
    /'
    0.62
    /
    0.62
    н
    0.61
    нкт
    0.60
    setPosition
    0.60
    ori
    0.58
    р
    0.58
    ism
    0.57
    POSITIVE LOGITS
     cientos
    1.02
     hundreds
    1.01
     hundert
    1.00
     decenas
    1.00
     thousands
    0.99
     dozens
    0.96
     milhares
    0.96
     दर्जन
    0.90
     millones
    0.89
     हजारों
    0.88
    Activations Density 0.096%

    No Known Activations