© 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. 73338
    Prev
    Next
    INDEX
    Explanations

    distance measurements

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

    The neuron activates on tokens denoting measured distances (numeric lengths with units, e.g. miles, meters, yards, km, feet) in spatial contexts.

    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
     možno
    -1.09
    おわりに
    -1.08
    等等
    -0.98
     informace
    -0.98
     spiega
    -0.98
    　　(
    -0.98
    autoComplete
    -0.96
    手数料
    -0.96
    Послед
    -0.96
    when
    -0.95
    POSITIVE LOGITS
     away
    1.38
     of
    1.30
    ずつ
    1.27
    ⅖
    1.18
    unggah
    1.11
    からだ
    1.10
    ridescent
    1.05
    madeus
    1.04
     hadden
    1.03
    partum
    1.03
    Activations Density 0.017%

    No Known Activations