© 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. 32776
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and attributes

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

    The neuron is detecting the words that introduce or label factual data fields (e.g. the “X is,” “X from,” or “X on:” that head off structured metadata entries).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ซึ่ง
    -1.02
    <bos>
    -1.02
     they
    -1.00
     puisque
    -0.96
    擅长
    -0.94
     ი
    -0.91
     उन
    -0.89
    ेशा
    -0.89
     puisqu
    -0.89
    がこの
    -0.88
    POSITIVE LOGITS
     a
    1.23
    rometry
    1.18
     an
    1.06
    ۠
    1.02
     führten
    1.01
     beragam
    1.00
     erhielten
    0.97
    址
    0.97
     in
    0.96
    minator
    0.96
    Activations Density 0.001%

    No Known Activations