© 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. 34-GEMMASCOPE-RES-131K
    7. 62480
    Prev
    Next
    INDEX
    Explanations

    xml parsing and code structure

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

    The neuron fires strongly on the very first line (the title or headline) of each question block.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Worms
    -0.84
     négatif
    -0.82
    शन
    -0.82
     Giochi
    -0.79
     femoral
    -0.75
     čern
    -0.74
     שנה
    -0.73
    Oscar
    -0.72
    Année
    -0.72
    rawd
    -0.72
    POSITIVE LOGITS
     começa
    0.90
    ὺς
    0.84
     eventType
    0.79
    eventType
    0.79
    orcid
    0.79
     Kazim
    0.77
    nameof
    0.76
     events
    0.76
    ruma
    0.75
     asociado
    0.75
    Activations Density 0.004%

    No Known Activations