© 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. 12620
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

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

    The neuron fires on markup and styling tokens—HTML tag names (like h1, h2, h3, span, b) and CSS/inline‐style specifications (font‐size values, pixel/percent units, bold attributes)—i.e. formatting directives in code.

    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
     razie
    -0.95
    fourth
    -0.94
    ]='\
    -0.89
    клу
    -0.88
    hankelijk
    -0.85
     üblichen
    -0.84
    ādā
    -0.82
     garantía
    -0.82
    east
    -0.82
    ประมาณ
    -0.82
    POSITIVE LOGITS
    ABASES
    0.94
    bootstrapcdn
    0.92
    (&:
    0.86
    dafrika
    0.83
     mourut
    0.83
    ɵɵelementEnd
    0.83
    车子
    0.82
     ім
    0.81
    RICULUM
    0.81
    晄
    0.80
    Activations Density 0.003%

    No Known Activations