© 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. 10-GEMMASCOPE-RES-131K
    7. 68507
    Prev
    Next
    INDEX
    Explanations

    programmatic, Stub, declaration, clavic, time, MAN

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

    The neuron flags uncommon, domain-specific content words or technical terms (e.g. “programmatic,” “declaration,” “clavicular,” “Grenadines,” “Stub”).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </h2>
    -2.09
    を行いました
    -1.63
    .《
    -1.52
    allez
    -1.52
    ﺲ
    -1.48
     splet
    -1.48
    grup
    -1.48
     Rabatt
    -1.47
     vecchio
    -1.45
     preocupado
    -1.44
    POSITIVE LOGITS
     “
    1.77
    er
    1.69
    ite
    1.66
    Ꮮ
    1.55
    ureusement
    1.50
    мите
    1.50
    nya
    1.47
    r
    1.46
     commodi
    1.46
    es
    1.45
    Activations Density 0.103%

    No Known Activations