© 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. 10786
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric tokens—especially floating-point and other measurement values—i.e. it detects 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_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
    shifted
    0.53
    sem
    0.50
    SetStr
    0.50
     ⿱
    0.50
    लेज
    0.50
    sort
    0.49
     đẩy
    0.49
     iff
    0.48
     nondegenerate
    0.48
    ্লে
    0.48
    POSITIVE LOGITS
     bezieht
    0.71
     subscript
    0.69
     selanjutnya
    0.69
     chodzi
    0.69
     subscripts
    0.69
     denotes
    0.68
     '-'
    0.67
     ':'
    0.67
     ‘
    0.66
     буква
    0.66
    Activations Density 0.024%

    No Known Activations