© 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. 66040
    Prev
    Next
    INDEX
    Explanations

    .go files

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

    The neuron activates on runs of whitespace (especially multi-space indentation) in code or markup.

    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
    new
    -1.41
    の為
    -1.11
     in
    -0.97
    for
    -0.96
     incluyendo
    -0.95
     of
    -0.94
    gsub
    -0.90
    the
    -0.90
     neue
    -0.90
    New
    -0.89
    POSITIVE LOGITS
     asesor
    1.07
     もう
    1.07
     podczas
    1.07
     प्रयास
    1.05
    Salz
    1.03
     Rechten
    1.02
     coussin
    1.02
    odetic
    1.01
    Außerdem
    1.01
     naveg
    0.99
    Activations Density 0.002%

    No Known Activations