© 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. 127982
    Prev
    Next
    INDEX
    Explanations

    This neuron detects icon–related CSS class names (e.g., “fa” or “glyphicon”) in HTML.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    icon prefixes and following characters

    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
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -1.37
    ↵
    -1.18
     In
    -1.17
     silnika
    -1.15
     With
    -1.12
     Even
    -1.11
     The
    -1.10
     includes
    -1.10
     after
    -1.09
     specific
    -1.09
    POSITIVE LOGITS
     of
    1.30
     teras
    1.17
     termen
    1.17
     docent
    1.13
    Ꮓ
    1.13
     panor
    1.12
     sacra
    1.10
     Reproduce
    1.09
    вина
    1.09
     cupid
    1.09
    Activations Density 0.000%

    No Known Activations