© 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. 6277
    Prev
    Next
    INDEX
    Explanations

    math, calculations, and formulas

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

    The neuron activates on numeric formula results—i.e. decimal numbers (floating-point values) appearing in the text.

    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
    加え
    0.96
    <0x80>
    0.85
     dall
    0.83
    <h3>
    0.81
     Ernst
    0.80
     Wittgenstein
    0.79
     unters
    0.76
    fait
    0.76
     Sist
    0.75
     Pepsi
    0.73
    POSITIVE LOGITS
    푅
    0.96
    కు
    0.96
     방정식
    0.89
    த்திற்கு
    0.88
    nj
    0.88
    ത്തിലേക്ക്
    0.86
    YH
    0.86
     بلد
    0.85
    ને
    0.84
     байланы
    0.83
    Activations Density 0.006%

    No Known Activations