© 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. 25030
    Prev
    Next
    INDEX
    Explanations

    keywords followed by definition

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

    The neuron fires on uppercase or capitalized field names immediately followed by a colon (e.g. “Date:”, “Time:”, “Configuration:”, “CategoryName:”, “labels:”, “ports:”), i.e. keys in config‐ or metadata‐style key:value pairs.

    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
     at
    -0.97
    está
    -0.94
    People
    -0.91
     over
    -0.88
     with
    -0.88
     came
    -0.87
    ........
    -0.84
    There
    -0.82
     想
    -0.79
    Бы
    -0.79
    POSITIVE LOGITS
    踯
    0.93
     lagerfeld
    0.90
    
    0.90
    crest
    0.89
     historische
    0.88
    گزاری
    0.88
    慫
    0.88
    IONES
    0.87
     白い
    0.86
    横に
    0.86
    Activations Density 0.080%

    No Known Activations