© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4396
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (especially multi‐digit numbers and decimals).

    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
    之前的
    0.79
    之前
    0.74
     Februar
    0.71
    其
    0.69
     अप्रैल
    0.67
    有人
    0.67
    April
    0.65
    यह
    0.64
    﨑
    0.64
    February
    0.63
    POSITIVE LOGITS
    _
    0.86
     원하는
    0.78
     함수
    0.75
    ไหน
    0.74
    :
    0.73
     ganglion
    0.72
    อะไร
    0.72
     settings
    0.69
    อยาก
    0.68
     helt
    0.68
    Activations Density 0.017%

    No Known Activations