© 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. 128247
    Prev
    Next
    INDEX
    Explanations

    measuring distance or how far away

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

    The neuron detects mentions of distance—particularly the words “distance” and “far” (and their variants) indicating how far something is.

    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
    橚
    -1.74
    klart
    -1.73
    ୈ
    -1.73
    蒾
    -1.69
    赑
    -1.55
     meine
    -1.54
    ⢊
    -1.54
     hotelu
    -1.52
    勠
    -1.48
    
    -1.45
    POSITIVE LOGITS
     from
    1.79
     which
    1.67
     distance
    1.61
     you
    1.52
     Our
    1.47
    ’
    1.45
     away
    1.40
     it
    1.39
    distance
    1.38
     '
    1.34
    Activations Density 0.097%

    No Known Activations