© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68422
    Prev
    Next
    INDEX
    Explanations

    HTML table headers or data

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

    The neuron primarily detects HTML tags (e.g. tokens like `<th>`, `<meta>`, `<td>`).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     its
    -1.81
     or
    -1.70
     really
    -1.57
     all
    -1.52
     it
    -1.44
     started
    -1.42
     only
    -1.41
     an
    -1.41
     from
    -1.40
     went
    -1.37
    POSITIVE LOGITS
     récupérer
    1.30
    
    1.19
     remporté
    1.14
    延伸閱讀
    1.13
     pratiquer
    1.11
     ragazzo
    1.10
     dilapidated
    1.10
     remplacer
    1.10
     aktualisiert
    1.09
     muni
    1.08
    Activations Density 0.000%

    No Known Activations