© 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. 10-GEMMASCOPE-RES-131K
    7. 10319
    Prev
    Next
    INDEX
    Explanations

    programming code structures

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

    CSS class names or identifiers related to layout and styling (particularly "clearfix", "container-fluid", "ButtonToolbar", "Form", and similar UI component class names).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is highly sensitive to hyphenated identifiers—especially CSS utility class names (e.g. “clearfix”, “container-fluid”, “table-responsive”).

    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
        
    -2.00
    捋
    -1.77
    了很多
    -1.76
    に来
    -1.65
    哙
    -1.57
    などが
    -1.56
    渐渐
    -1.55
    𐬹
    -1.55
     sinds
    -1.54
    </h3>
    -1.53
    POSITIVE LOGITS
     with
    2.66
    What
    2.05
    Before
    1.95
    There
    1.84
    This
    1.77
    Entrevista
    1.75
     краще
    1.73
    While
    1.70
    when
    1.70
     one
    1.67
    Activations Density 0.001%

    No Known Activations