© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45391
    Prev
    Next
    INDEX
    Explanations

    throws Exception

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

    The neuron is picking up on leading indentation/whitespace tokens (e.g. the spaces before and including opening braces) that mark the start of a code block.

    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
    borderSide
    -1.66
    antism
    -1.63
    '
    -1.57
    ulfon
    -1.51
    ERS
    -1.48
     respostas
    -1.42
    pherical
    -1.41
     Its
    -1.41
     étrange
    -1.41
    if
    -1.40
    POSITIVE LOGITS
    》。
    1.48
    》，
    1.43
     sabemos
    1.39
     Bedür
    1.38
     esperamos
    1.36
     */
    1.35
    sandalia
    1.34
     jotka
    1.33
    ꧂
    1.30
    unikasi
    1.29
    Activations Density 0.008%

    No Known Activations