© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35021
    Prev
    Next
    INDEX
    Explanations

    presence within a group

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

    This neuron specifically detects occurrences of the word “among.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    '
    -2.59
     
    -2.33
     ‘
    -2.28
    -2.23
    遑
    -2.22
     '
    -2.20
     is
    -2.17
    出来ました
    -1.96
     issue
    -1.93
     {
    -1.91
    POSITIVE LOGITS
    ௅
    2.67
    ܇
    2.58
    綃
    2.55
    pecabe
    2.36
    ࣭
    2.33
    喼
    2.33
    ﮯ
    2.28
     dezelve
    2.23
     phénom
    2.23
     水彩
    2.22
    Activations Density 0.024%

    No Known Activations