© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59585
    Prev
    Next
    INDEX
    Explanations

    professional councils and licensing

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

    The neuron activates on numeric tokens—especially multi-digit numbers such as years, case citations, dates, and other numerical references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tendances
    -0.77
    onate
    -0.75
     Void
    -0.74
    tigs
    -0.73
    essandro
    -0.70
     segura
    -0.70
     sebanyak
    -0.69
    nss
    -0.68
    HasValue
    -0.67
     autopsy
    -0.67
    POSITIVE LOGITS
     regulatory
    1.65
     council
    1.58
     Council
    1.48
     regulator
    1.47
     regulators
    1.45
     licensing
    1.44
     registration
    1.42
     councils
    1.41
    Council
    1.41
     professional
    1.41
    Activations Density 0.040%

    No Known Activations