© 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. 34-GEMMASCOPE-RES-131K
    7. 92744
    Prev
    Next
    INDEX
    Explanations

    distances to locations

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

    The neuron detects numeric expressions specifying distances or travel times (e.g. “7 km away,” “15 minutes’ walk”).

    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
     Muskel
    -0.95
    autoComplete
    -0.93
     támogat
    -0.93
     Gewebe
    -0.91
    ıca
    -0.90
     zostać
    -0.89
     escalada
    -0.89
     Brücke
    -0.89
     Brücken
    -0.88
     costura
    -0.86
    POSITIVE LOGITS
     away
    2.11
     of
    1.34
     from
    1.14
     jauh
    1.06
    away
    0.96
    錳
    0.90
     दोनों
    0.90
    Herzlich
    0.90
    Willkommen
    0.89
     off
    0.83
    Activations Density 0.011%

    No Known Activations