© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39643
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and numbers

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

    It detects the occurrence of the set‐intersection operator token (“cap”) in mathematical expressions.

    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
    anstal
    -0.95
     хочет
    -0.92
     bancaria
    -0.84
    已被
    -0.84
     Dreamer
    -0.82
    левой
    -0.82
     already
    -0.82
    
    -0.82
     ресто
    -0.81
     Fract
    -0.81
    POSITIVE LOGITS
     pareció
    1.13
    还有一个
    1.11
     lavorare
    1.05
     three
    1.01
     parecía
    0.96
    Suerte
    0.95
     dijeron
    0.94
     trois
    0.94
     uwagę
    0.93
    تحميل
    0.92
    Activations Density 0.062%

    No Known Activations