© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19488
    Prev
    Next
    INDEX
    Explanations

    html attribute assignment

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

    The neuron fires on HTML attribute definitions and their values—especially inline styling and layout attributes (e.g. style="…", width:…, id="…", class="…", data-…="…").

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

    No Comments

    Negative Logits
     to
    -1.58
    );
    -1.34
    begin
    -1.22
     확인함
    -1.08
     able
    -1.08
     include
    -1.05
     first
    -1.05
    </strong>
    -1.05
    ファイル
    -1.05
     दोनों
    -1.04
    POSITIVE LOGITS
     ས
    1.30
     ();
    
    1.22
    場所に
    1.21
    äldrar
    1.20
    Ivoire
    1.18
    したのは
    1.18
    ってしまった
    1.16
     ]}
    1.13
    ิต
    1.12
     ';
    
    1.11
    Activations Density 0.049%

    No Known Activations