© 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. 22-GEMMASCOPE-RES-131K
    7. 26371
    Prev
    Next
    INDEX
    Explanations

    distance measurement

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

    The neuron activates on occurrences of the word “distance” (and close variants like “dist” or “equidistance”) in the text.

    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
    棡
    -2.73
    嵛
    -2.70
    栳
    -2.61
     This
    -2.48
    廡
    -2.47
     acheté
    -2.44
    
    -2.42
    喁
    -2.41
     faceva
    -2.31
     paio
    -2.30
    POSITIVE LOGITS
    ),
    2.48
     Their
    2.45
    с
    2.41
    ?
    2.31
    ",
    2.30
     immerse
    2.30
     But
    2.28
     (
    2.28
    芎
    2.19
     acquire
    2.14
    Activations Density 0.014%

    No Known Activations