© 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. 15170
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on standalone floating‐point numeric literals (i.e. tokens that look like “1234.5678”).

    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
     '_
    0.79
     SPF
    0.79
     Flows
    0.75
     SP
    0.75
     Youtube
    0.74
     Size
    0.71
     '
    0.71
     Iphone
    0.71
     BUN
    0.71
     Scaling
    0.70
    POSITIVE LOGITS
    jährige
    0.93
    annya
    0.85
    evt
    0.85
     لپاره
    0.82
    Mm
    0.82
    ：（
    0.80
     yaşad
    0.79
    ക്കാരി
    0.79
     kendini
    0.79
    :“
    0.78
    Activations Density 0.000%

    No Known Activations