© 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. 15947
    Prev
    Next
    INDEX
    Explanations

    square roots and bypass mechanisms

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

    The neuron activates specifically on floating-point number tokens (i.e. numeric values containing a decimal point).

    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
    чный
    0.93
     рынке
    0.79
    фессиона
    0.77
    쑹
    0.77
     juta
    0.77
    니다
    0.75
     accesorios
    0.75
     artículos
    0.75
    binoculars
    0.75
    너지
    0.74
    POSITIVE LOGITS
     Headache
    0.79
     Fame
    0.76
     Diff
    0.75
     Dataset
    0.74
    早速
    0.73
    Mannschaft
    0.70
     Modifications
    0.70
    я
    0.70
     phép
    0.69
    殯
    0.69
    Activations Density 0.001%

    No Known Activations