© 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. 15604
    Prev
    Next
    INDEX
    Explanations

    code comments and libraries

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

    This neuron fires on standalone tokens that start with a capital letter (e.g. Ini, compiler, P, undefined, CLI, Helvetica, Pul).

    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
    荩
    -2.20
    H
    -2.03
    P
    -1.99
    玙
    -1.99
    衚
    -1.98
     hvis
    -1.96
    ↵
    -1.91
    L
    -1.90
    C
    -1.89
     verkau
    -1.88
    POSITIVE LOGITS
    There
    1.96
    峮
    1.91
     gratuito
    1.90
    These
    1.88
    this
    1.82
     може
    1.79
     cambiado
    1.76
     aprendido
    1.75
     comprado
    1.73
    Although
    1.72
    Activations Density 0.000%

    No Known Activations