© 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. 49154
    Prev
    Next
    INDEX
    Explanations

    locations and counties

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

    This neuron detects mentions of geographic place names and related location identifiers (towns, counties, streets, highways, 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
    Cm
    -0.73
    wich
    -0.72
    ONAUT
    -0.71
     empe
    -0.69
    tagen
    -0.67
    シン
    -0.66
    オル
    -0.65
     см
    -0.65
     fiss
    -0.65
    Embedded
    -0.65
    POSITIVE LOGITS
     Farmington
    1.09
    minmax
    0.88
     Chest
    0.75
     Potsdam
    0.74
     BOSS
    0.73
    త్ర
    0.73
     Malone
    0.72
    cellence
    0.71
    רוש
    0.71
    ać
    0.70
    Activations Density 0.035%

    No Known Activations