© 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. 22-GEMMASCOPE-RES-131K
    7. 72356
    Prev
    Next
    INDEX
    Explanations

    commune and place names

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

    This neuron detects the capitalized name fragments of municipalities or communes in administrative‐division lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     by
    -1.80
     in
    -1.57
     with
    -1.55
     would
    -1.49
     start
    -1.45
     panas
    -1.45
     on
    -1.40
     casas
    -1.38
     probably
    -1.36
     podio
    -1.36
    POSITIVE LOGITS
     erwähnten
    1.52
    ченное
    1.41
     gewähr
    1.38
     vendus
    1.36
     concernés
    1.36
    就没有
    1.34
     rechercher
    1.31
     déterminer
    1.27
     déposer
    1.27
     {?>
    1.24
    Activations Density 0.014%

    No Known Activations