© 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. 22-GEMMASCOPE-RES-131K
    7. 67416
    Prev
    Next
    INDEX
    Explanations

    i i i values

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

    The neuron chiefly activates on LaTeX‐style math expressions and numeric or math‐symbol tokens (e.g. dollar signs, variable names, digits).

    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
     it
    -1.13
     Sünde
    -0.94
     And
    -0.88
     มัน
    -0.87
    ところ
    -0.86
    archical
    -0.85
    тельством
    -0.84
    よりも
    -0.84
     nogle
    -0.82
    峮
    -0.81
    POSITIVE LOGITS
    +"_
    1.10
    جميع
    1.09
    ícias
    1.08
     Système
    1.08
    太多了
    1.05
     usize
    1.05
    AddHtmlAttribute
    1.04
    
    1.04
    ensä
    1.03
    প্র
    1.03
    Activations Density 0.009%

    No Known Activations