© 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. 47293
    Prev
    Next
    INDEX
    Explanations

    National Professional Training Statistics

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

    The neuron fires on named‐entity and metadata tokens—proper names, titles, organizations, positions, and other infobox‐style labels.

    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
     lookup
    -0.73
     recovery
    -0.70
    inquirer
    -0.70
     deposition
    -0.70
     turbulence
    -0.69
    atoren
    -0.69
    SCAN
    -0.69
     no
    -0.67
    langes
    -0.67
     Hutchins
    -0.66
    POSITIVE LOGITS
    トゥー
    0.80
    ilesh
    0.77
    Kuro
    0.77
    ensee
    0.76
     breiten
    0.76
     smartwatch
    0.75
    Uid
    0.75
    wiec
    0.74
     cath
    0.73
    GameMode
    0.72
    Activations Density 0.006%

    No Known Activations