© 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. 104376
    Prev
    Next
    INDEX
    Explanations

    text boxes and input fields

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

    the word "box" or "boxes" in programming contexts, particularly when discussing UI input elements like text boxes and checkboxes.

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

    The neuron fires on occurrences of the phrase “text box” (including its plural “text boxes”).

    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
     aspetta
    -1.91
    ↵
    -1.88
    </b>
    -1.74
     trovano
    -1.69
    1
    -1.68
    ');
    -1.67
    ”,
    -1.66
    re
    -1.65
    ”?
    -1.64
    3
    -1.59
    POSITIVE LOGITS
     are
    1.96
     ďal
    1.93
     pidiendo
    1.88
    ция
    1.79
     další
    1.77
    </sub>
    1.76
    )});
    1.76
    </h3>
    1.75
    ꔹ
    1.73
     Photocase
    1.70
    Activations Density 0.040%

    No Known Activations