© 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. 13317
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on numeric tokens containing a decimal point (i.e., 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
    ל
    0.91
    јан
    0.83
    り
    0.79
    ја
    0.77
    한
    0.75
    お
    0.73
     પ
    0.72
    미
    0.72
    ia
    0.71
    ъл
    0.71
    POSITIVE LOGITS
     depictions
    1.00
     proteins
    0.95
     nightmares
    0.89
     stabilizers
    0.89
     stabilizes
    0.86
     replicas
    0.85
     clove
    0.85
     delicacies
    0.82
     infestations
    0.82
     antiviral
    0.80
    Activations Density 0.000%

    No Known Activations