© 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. 59370
    Prev
    Next
    INDEX
    Explanations

    provinces and districts

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

    The neuron fires on digits, numeric codes, and number‐related tokens (years, IDs, measurements, etc.).

    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
     Cyprus
    -0.82
     電
    -0.78
     solteiro
    -0.76
     Calabria
    -0.75
     Mauritius
    -0.75
    tü
    -0.74
     mali
    -0.74
    ‥
    -0.74
    ỏi
    -0.73
     teka
    -0.73
    POSITIVE LOGITS
     provinces
    1.59
     province
    1.29
     Regions
    1.28
     Province
    1.27
     Region
    1.26
     Provinces
    1.23
     districts
    1.20
    Province
    1.13
     district
    1.11
     Districts
    1.09
    Activations Density 0.066%

    No Known Activations