© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35842
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

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

    The neuron consistently lights up on content-bearing nouns—especially technical terms and proper names—rather than on common function words.

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

    No Comments

    Negative Logits
    vignette
    -1.13
     costuras
    -1.11
     manquer
    -1.09
    mizuno
    -1.06
    sore
    -1.04
     réfugi
    -1.02
     cantidades
    -1.00
    irsi
    -1.00
     élimin
    -0.97
    фициальный
    -0.97
    POSITIVE LOGITS
     in
    1.36
     "
    1.17
     }^{
    1.04
    <table>
    0.93
    <td>
    0.92
    u
    0.90
    ."
    0.90
    Formatter
    0.89
    In
    0.87
    ¢
    0.87
    Activations Density 0.294%

    No Known Activations