© 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. 34-GEMMASCOPE-RES-131K
    7. 97786
    Prev
    Next
    INDEX
    Explanations

    loading and spinner

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

    The neuron fires on programming‐language identifiers—especially HTML/JS/CSS IDs, variable/class names, and other code tokens—i.e. it detects code identifiers in snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Dewan
    -0.77
     unjust
    -0.76
    农场
    -0.75
    携带
    -0.74
     Memphis
    -0.73
    انیه
    -0.72
     Vanderbilt
    -0.71
     桌面
    -0.71
     kraf
    -0.70
     Isten
    -0.69
    POSITIVE LOGITS
     loading
    5.69
     Loading
    4.84
    loading
    4.69
    Loading
    4.63
     loader
    3.72
    LOADING
    3.56
     LOADING
    3.53
    loader
    3.34
    Loader
    3.33
     Loader
    3.22
    Activations Density 0.087%

    No Known Activations