© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41792
    Prev
    Next
    INDEX
    Explanations

    then, however, allowed

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

    This neuron detects unusually long runs of space characters (large whitespace/indentation) 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_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
     rayures
    -2.47
     acteurs
    -2.39
     gustaMe
    -2.31
     leſs
    -2.31
     Dinas
    -2.30
     tiroirs
    -2.30
     imponer
    -2.28
     ſever
    -2.27
     itinéraires
    -2.23
     trajets
    -2.22
    POSITIVE LOGITS
     to
    3.89
     more
    2.78
     When
    2.75
     on
    2.72
     first
    2.67
     only
    2.61
     just
    2.59
     so
    2.58
     can
    2.55
     In
    2.53
    Activations Density 0.031%

    No Known Activations