© 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. 66962
    Prev
    Next
    INDEX
    Explanations

    walking distance from places

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

    The neuron fires on mentions of walking routes or distances, especially words like “walk,” “walking,” “sidewalks,” and “distance” indicating pedestrian directions.

    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
    <
    -1.52
     –
    -1.51
    i
    -1.45
    .
    -1.45
    f
    -1.38
    x
    -1.36
    it
    -1.35
    k
    -1.33
    ps
    -1.32
    gen
    -1.32
    POSITIVE LOGITS
    capulco
    1.48
    櫺
    1.46
     fortalec
    1.46
    🔚
    1.38
    🚶
    1.38
    hellip
    1.37
    鰨
    1.37
    ğın
    1.34
    (^^)
    1.30
    屄
    1.30
    Activations Density 0.018%

    No Known Activations