© 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. 99833
    Prev
    Next
    INDEX
    Explanations

    place names and proper nouns

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

    The neuron fires on span tokens that are place names (cities, counties, etc.), i.e. geographic location 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_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
     [
    -1.74
    ”
    -1.70
    たち
    -1.59
     treacherous
    -1.50
    ag
    -1.45
     ”
    -1.45
     I
    -1.41
    ?”
    -1.33
    ol
    -1.32
     “
    -1.32
    POSITIVE LOGITS
     Secondo
    1.49
     Oltre
    1.48
     vostre
    1.48
    酲
    1.46
     Perché
    1.45
     medals
    1.45
    淠
    1.45
     kapal
    1.44
     Función
    1.43
     Ejec
    1.42
    Activations Density 0.572%

    No Known Activations