© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 98990
    Prev
    Next
    INDEX
    Explanations

    lists of names

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

    The neuron fires on the names of musical artists (proper nouns) when they’re listed.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     dió
    -1.55
     vorhandenen
    -1.50
    Muerte
    -1.39
    实在是
    -1.38
    vantaged
    -1.36
     alza
    -1.35
     calzado
    -1.32
    ihnachten
    -1.31
    ondissement
    -1.30
    Istorija
    -1.27
    POSITIVE LOGITS
     whom
    1.78
    </h1>
    1.63
     ‘
    1.51
     and
    1.44
     who
    1.37
     to
    1.37
     of
    1.33
     whome
    1.33
     gues
    1.30
    ;
    1.30
    Activations Density 0.050%

    No Known Activations