© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67765
    Prev
    Next
    INDEX
    Explanations

    distance within proximity

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

    The main thing this neuron does is detect numeric tokens representing measurements (especially distances and quantities).

    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
    Exactly
    -1.06
    Concerning
    -1.06
     bekam
    -1.06
    Authenticate
    -1.03
     マーク
    -1.02
     記事
    -1.02
     tendenza
    -1.00
     provoquer
    -0.99
     gött
    -0.97
     präsenti
    -0.96
    POSITIVE LOGITS
     of
    1.71
     radius
    1.45
     where
    1.34
     vicinity
    1.20
     around
    1.18
     radii
    1.17
     surrounding
    1.15
     including
    1.08
    radius
    1.05
     jossa
    1.02
    Activations Density 0.019%

    No Known Activations