© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15651
    Prev
    Next
    INDEX
    Explanations

    locations and surroundings

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

    The neuron fires on generic references to venues or locations (e.g. “place,” “places,” “establishment”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Màu
    -1.55
    𓍊
    -1.53
     küm
    -1.52
    calciatore
    -1.50
    rådet
    -1.48
     forskjellige
    -1.48
     pagrind
    -1.46
     rijden
    -1.45
     meteen
    -1.44
     gekozen
    -1.41
    POSITIVE LOGITS
     They
    1.87
    ：……
    1.81
    迸
    1.67
    la
    1.66
     empfind
    1.65
     ….
    1.59
     was
    1.56
    entikan
    1.52
     to
    1.50
     is
    1.43
    Activations Density 0.004%

    No Known Activations