© 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. 84769
    Prev
    Next
    INDEX
    Explanations

    examples or explanations

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

    This neuron detects occurrences of the phrase “by way of.”

    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
     theres
    -2.17
     leichter
    -1.98
    可以使用
    -1.92
     الفلسط
    -1.88
    which
    -1.88
     wholly
    -1.80
     aéreas
    -1.80
    主催
    -1.79
    日曜日
    -1.78
     seleccionadas
    -1.78
    POSITIVE LOGITS
    ,
    2.28
    
    2.11
    痦
    2.05
    𖣔
    2.00
    蛩
    1.95
    狃
    1.91
    芣
    1.91
     Namun
    1.91
    '>
    1.84
    ᚔ
    1.84
    Activations Density 0.009%

    No Known Activations