© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12254
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or units

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

    The main thing this neuron does is detect numeric tokens and other numerical expressions (measurements, dimensions, variable 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_31_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
     amazement
    0.56
     eind
    0.55
     amaz
    0.55
    ,]$
    0.55
     অন্যান্য
    0.54
    、（
    0.54
    大家的
    0.54
    其他
    0.54
    Toy
    0.53
     خب
    0.53
    POSITIVE LOGITS
     ×
    1.20
     ÷
    1.12
     vs
    1.00
    ×
    0.99
     versus
    0.98
    ÷
    0.88
     बनाम
    0.84
     minus
    0.84
     плюс
    0.82
     Versus
    0.82
    Activations Density 0.149%

    No Known Activations