© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73744
    Prev
    Next
    INDEX
    Explanations

    geographic place names

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

    The neuron activates on proper nouns that are place names or geographic locations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    of
    -2.31
    al
    -2.03
    el
    -1.91
    in
    -1.91
    <strong>
    -1.79
    t
    -1.76
    ",
    -1.73
    e
    -1.73
    at
    -1.62
    la
    -1.62
    POSITIVE LOGITS
     legen
    1.59
    
    1.55
     usado
    1.54
     usadas
    1.52
    Paket
    1.50
    ênis
    1.48
    小声
    1.47
     oculto
    1.46
    nomor
    1.45
     divertido
    1.45
    Activations Density 0.900%

    No Known Activations