© 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. 127609
    Prev
    Next
    INDEX
    Explanations

    articles, news, and specific items

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

    The neuron fires on named entities—especially person names, titles (e.g. “Senator Sam Brownback”), and publication or article names.

    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
     with
    -1.93
     from
    -1.88
     in
    -1.88
     menjadi
    -1.80
     by
    -1.80
     without
    -1.76
     changed
    -1.60
     an
    -1.59
     during
    -1.59
     or
    -1.56
    POSITIVE LOGITS
     padrões
    1.82
     весьма
    1.80
    惬
    1.80
     theſe
    1.75
     heretofore
    1.66
     πρ
    1.65
     tornillos
    1.63
     obligación
    1.56
    もあって
    1.56
     envoyé
    1.55
    Activations Density 0.503%

    No Known Activations