© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15619
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens containing decimal points (floating-point numbers).

    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
    но
    0.73
    jun
    0.72
    radiated
    0.71
    no
    0.71
    mot
    0.70
     váš
    0.70
    ̃
    0.69
    ct
    0.68
    refour
    0.68
    á
    0.68
    POSITIVE LOGITS
    芙
    0.81
     コンパクト
    0.78
     banged
    0.76
    ਫ
    0.75
    めの
    0.75
     بری
    0.72
     វា
    0.72
    <bos>
    0.71
    就需要
    0.71
    zimmer
    0.71
    Activations Density 0.000%

    No Known Activations