© 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. 15268
    Prev
    Next
    INDEX
    Explanations

    This neuron detects floating-point numeric literals (tokens containing decimal 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
    s
    0.81
    od
    0.78
    زيد
    0.78
    з
    0.76
    is
    0.75
    sons
    0.72
    x
    0.71
    or
    0.70
    ز
    0.69
    bid
    0.68
    POSITIVE LOGITS
     때
    0.88
    ……”
    0.82
     hateful
    0.78
     ね
    0.77
     counterfeit
    0.77
     Dolce
    0.76
     उन्ह
    0.75
     dubious
    0.75
    ᖕ
    0.75
     آنها
    0.74
    Activations Density 0.001%

    No Known Activations