© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13720
    Prev
    Next
    INDEX
    Explanations

    certification

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens (especially multi‐digit or decimal 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
    堌
    0.59
    dsale
    0.59
     translational
    0.57
    arctan
    0.57
    translational
    0.56
     perfusion
    0.55
     amortization
    0.55
     Augustin
    0.55
    冭
    0.55
    grams
    0.54
    POSITIVE LOGITS
     certification
    1.30
     certificate
    1.27
     certify
    1.27
     Certification
    1.26
     Certificate
    1.25
     Cert
    1.23
     certifications
    1.23
     certificación
    1.21
    Certification
    1.17
     certificado
    1.16
    Activations Density 0.316%

    No Known Activations