© 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. 9693
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numeric tokens—especially multi‐digit sequences, decimals, or other number‐like strings.

    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
    B
    0.98
    ب
    0.86
    L
    0.83
    furt
    0.82
    T
    0.80
    بق
    0.80
    Made
    0.76
    ميم
    0.74
    FUR
    0.74
    ılar
    0.72
    POSITIVE LOGITS
     ambulatory
    0.93
    apaccay
    0.87
     radionu
    0.87
     मुख्यतः
    0.86
     primarily
    0.86
     spatially
    0.85
     casse
    0.83
     razón
    0.82
    乨
    0.82
     integrative
    0.81
    Activations Density 0.004%

    No Known Activations