© 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. 16646
    Prev
    Next
    INDEX
    Explanations

    component or template declaration

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

    The neuron fires on identifier tokens used as attribute/property names in JSX/XML‐style syntax (e.g. tag, component, template, name, default, method).

    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
    蔸
    -1.09
     чехол
    -1.08
    奩
    -1.05
     MADRID
    -1.04
     kapture
    -1.04
     gravidez
    -1.01
     TECHNIQUE
    -1.01
     RAILROAD
    -1.00
     SPANISH
    -1.00
     ilan
    -1.00
    POSITIVE LOGITS
     a
    1.59
     an
    1.40
     with
    1.33
     at
    1.18
     before
    1.17
     by
    1.13
     Before
    1.12
     what
    1.09
    Before
    1.09
     marvellous
    1.07
    Activations Density 0.006%

    No Known Activations