© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73219
    Prev
    Next
    INDEX
    Explanations

    fast enough

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

    The neuron specifically detects the word “fast” when it appears in the text.

    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
     
    -3.47
    迨
    -3.11
     “
    -2.77
      
    -2.75
     بالإضافة
    -2.59
    捋
    -2.53
    ݮ
    -2.52
     continúas
    -2.41
    になりますが
    -2.33
    先は
    -2.27
    POSITIVE LOGITS
     речо
    2.55
    ሖ
    2.50
    ꜆
    2.44
    鬭
    2.41
     اینترنتی
    2.41
    你的
    2.39
    嗵
    2.33
    禇
    2.30
    .
    2.30
     даже
    2.28
    Activations Density 0.007%

    No Known Activations