© 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. 31-GEMMASCOPE-2-RES-16K
    7. 145
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric tokens (numbers, especially measurements or quantities, including multi‐digit and decimal 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_31_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
    <unused27>
    0.50
    ètent
    0.49
    akarane
    0.49
    餑
    0.49
    য্
    0.49
    ottak
    0.49
    <unused23>
    0.48
    <unused42>
    0.48
    য়োজন
    0.48
    ákat
    0.47
    POSITIVE LOGITS
    0.84
    1
    0.66
    8
    0.62
    5
    0.61
    2
    0.60
    6
    0.59
    4
    0.57
    9
    0.57
     $
    0.57
    3
    0.56
    Activations Density 0.478%

    No Known Activations