© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4715
    Prev
    Next
    INDEX
    Explanations

    html tags

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

    The neuron strongly responds to HTML tags and link markup (e.g. anchor tags, span/div tags, fused‐text or URL shortcode markers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aspen
    0.65
     pertama
    0.65
     cannon
    0.64
     G
    0.64
     monde
    0.64
     pepper
    0.64
     loam
    0.64
     abstra
    0.64
    棗
    0.64
     cage
    0.63
    POSITIVE LOGITS
    ↵
    0.78
    <tr>
    0.76
     이에
    0.73
    </li>
    0.72
    าร
    0.72
    きっと
    0.69
    (['
    0.66
     làng
    0.65
    camiseta
    0.65
    toLocale
    0.65
    Activations Density 0.000%

    No Known Activations