© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118226
    Prev
    Next
    INDEX
    Explanations

    vs. or versus

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

    The neuron fires most strongly on key heading or title words (proper‐noun or section‐title tokens) that appear in document headings or section labels.

    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
     calling
    -0.77
    痕
    -0.77
     Arkansas
    -0.75
     FB
    -0.72
     experts
    -0.72
     exquisite
    -0.71
     voorbere
    -0.70
    ico
    -0.70
     рэ
    -0.70
    XMLSchema
    -0.69
    POSITIVE LOGITS
     Virginia
    1.22
     VIRGINIA
    1.20
     Atención
    1.09
    Virginia
    1.09
     virginia
    1.05
     Charlottesville
    1.04
    VIR
    0.97
     اليمن
    0.92
     Northam
    0.91
    schools
    0.90
    Activations Density 0.001%

    No Known Activations