© 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. 22-GEMMASCOPE-RES-131K
    7. 24982
    Prev
    Next
    INDEX
    Explanations

    Epilepsy syndrome

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

    empty lines or whitespace between paragraphs in text documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron activates strongly on large whitespace or blank‐line separators, i.e. paragraph breaks.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Menurut
    -1.16
    Į
    -1.05
    ɪ
    -1.04
    擔心
    -1.02
    ĭ
    -1.01
    malige
    -1.01
    grees
    -1.00
    Ī
    -0.99
    担心
    -0.98
    Жен
    -0.98
    POSITIVE LOGITS
     will
    1.40
     and
    1.30
     no
    1.28
     family
    1.18
     his
    1.16
     we
    1.14
     anyone
    1.09
    ticale
    1.08
    Transcriptie
    1.05
     donations
    1.04
    Activations Density 0.000%

    No Known Activations