© 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. 56978
    Prev
    Next
    INDEX
    Explanations

    education, professional, house, editor, abstract, college

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

    The neuron fires on tokens that signal statistical or demographic reporting (e.g. survey methodology, sample sizes, and population/economic data).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ПРО
    -0.81
     hemma
    -0.79
    āng
    -0.77
    Dimensional
    -0.76
     مجلسی
    -0.75
     campesinos
    -0.75
     arah
    -0.74
    KJV
    -0.74
    orithmic
    -0.74
    cedentes
    -0.74
    POSITIVE LOGITS
    Universe
    0.95
     householder
    0.88
     Zitron
    0.85
     PCT
    0.82
     Universe
    0.77
    specular
    0.76
    vdots
    0.75
     universe
    0.74
    umbered
    0.74
    不過
    0.73
    Activations Density 0.007%

    No Known Activations