© 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. 98043
    Prev
    Next
    INDEX
    Explanations

    xml declaration

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

    This neuron detects long sequences of alphanumeric strings and punctuation typical of URLs, file paths, or API identifiers.

    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
     台灣
    -0.73
     Мі
    -0.72
     inline
    -0.70
    صال
    -0.70
    Unidad
    -0.68
     Extraction
    -0.65
    bows
    -0.65
    Comput
    -0.64
     responden
    -0.63
     Unlimited
    -0.62
    POSITIVE LOGITS
     AMAZON
    0.98
    Launch
    0.97
     launch
    0.90
     Launch
    0.89
    APL
    0.88
    hintText
    0.87
     Amazon
    0.85
    Amazon
    0.82
     speech
    0.79
    0.79
    Activations Density 0.012%

    No Known Activations