© 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. 16582
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron is picking up on high‐level document metadata cues—tokens that appear in section headings or header information (e.g. “Launched,” “Sponsored,” “Justices,” “Opinion,” “by,” “Justice,” etc.).

    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
     their
    -1.73
     église
    -1.19
     these
    -1.13
     this
    -1.12
     Dette
    -1.05
    cción
    -1.05
     recevrez
    -1.05
    itize
    -1.04
    ==-
    -1.02
     saken
    -1.02
    POSITIVE LOGITS
    Sied
    1.06
     mensuales
    1.05
     llorar
    1.05
     chuy
    1.05
    ussia
    1.02
    Lø
    0.97
    けどね
    0.95
     cucharadita
    0.95
     vort
    0.95
    ‌ی
    0.94
    Activations Density 0.002%

    No Known Activations