© 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. 22-GEMMASCOPE-RES-131K
    7. 127850
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on code identifiers for API operations or class/type names (i.e. CamelCase names like “GetBotAliases,” “Aliases,” etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    C++ AWS SDK includes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    ۞
    -1.23
     potes
    -1.20
     palav
    -1.10
     torba
    -1.07
    “……
    -1.06
     verba
    -1.06
     város
    -1.04
     coque
    -1.04
    ugd
    -0.98
     skolen
    -0.98
    POSITIVE LOGITS
     you
    1.24
    了一眼
    1.08
    빼
    1.05
    strerror
    1.03
    屬於
    1.02
    ination
    1.02
    [&
    0.98
     вам
    0.96
     liées
    0.96
     tevreden
    0.96
    Activations Density 0.013%

    No Known Activations