© 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. 103202
    Prev
    Next
    INDEX
    Explanations

    French cities and regions

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

    The neuron is detecting hyphenated segments in place names (e.g. the “-lès-”/“-Metz” parts of French town names).

    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
    rosos
    -0.73
    serial
    -0.71
     sachsen
    -0.69
     Gött
    -0.69
    <0xD5>
    -0.69
    PUBLISH
    -0.69
     agricoles
    -0.69
    prix
    -0.69
    EDES
    -0.68
     Oxford
    -0.68
    POSITIVE LOGITS
     Strasbourg
    1.38
     Alsace
    1.21
     sauer
    0.97
    aliana
    0.93
     Schmitt
    0.92
    Alsace
    0.90
     WIS
    0.89
    Milwaukee
    0.85
    uebe
    0.85
     Saar
    0.84
    Activations Density 0.012%

    No Known Activations