© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76054
    Prev
    Next
    INDEX
    Explanations

    internet, TV, and satellite services

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

    The neuron fires on numeric tokens—sequences of digits (e.g. counts, phone numbers, percentages, measurements).

    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
     decathlon
    -0.86
     oun
    -0.81
     xiaomi
    -0.76
     SSN
    -0.75
     KYC
    -0.74
     ecosistema
    -0.74
     lenovo
    -0.71
     TSM
    -0.71
    MIA
    -0.70
     Echin
    -0.70
    POSITIVE LOGITS
     satellite
    2.34
     Satellite
    2.00
    Satellite
    1.80
     DSL
    1.72
     ADS
    1.65
    satellite
    1.65
    DSL
    1.62
     dial
    1.61
     wireless
    1.51
     fiber
    1.36
    Activations Density 0.080%

    No Known Activations