© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 114103
    Prev
    Next
    INDEX
    Explanations

    DOCTYPE declarations

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

    XML and HTML DOCTYPE declarations and URI path separators.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5

    The neuron strongly responds to the signature tokens of XML/HTML DOCTYPE declarations—especially the “PUBLIC” identifier and the double‐slash URLs pointing to DTD definitions.

    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
     or
    -1.88
    ’
    -1.70
     only
    -1.45
     for
    -1.45
     if
    -1.43
     even
    -1.42
     although
    -1.34
     betrek
    -1.34
     But
    -1.32
     could
    -1.27
    POSITIVE LOGITS
    蓠
    1.70
     pinpoint
    1.51
     Commencez
    1.48
    翃
    1.47
     Préférences
    1.47
    })}
    1.46
    %;
    
    1.46
    })();
    1.46
    ☑️
    1.45
     Pantalla
    1.45
    Activations Density 0.069%

    No Known Activations