© 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. 8851
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially decimal numbers or other multi‐digit numerical values.

    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
    ertel
    0.78
     întâm
    0.78
    기
    0.76
    이기
    0.76
    otification
    0.74
    RECTION
    0.73
    rées
    0.72
    ार्ड
    0.71
    ઓ
    0.71
    atrice
    0.70
    POSITIVE LOGITS
     analyse
    0.94
     Kafka
    0.93
     analysis
    0.90
     Analysis
    0.89
     Comercio
    0.88
     Analyse
    0.85
    Analysis
    0.84
     Еще
    0.84
     Aluminum
    0.83
     barcodes
    0.83
    Activations Density 0.003%

    No Known Activations