© 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. 10-GEMMASCOPE-RES-131K
    4. 41621
    Prev
    Next
    INDEX
    Explanations

    Visual Studio

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

    The neuron is triggered by occurrences of the capitalized word “Visual.”

    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
     Which
    -2.56
    你看
    -2.50
    
    -2.22
     Except
    -2.20
     Especially
    -2.20
     Unless
    -2.16
     ésta
    -2.16
     When
    -2.16
     While
    -2.14
     feita
    -2.14
    POSITIVE LOGITS
    a
    3.09
    و
    2.92
     zustand
    2.73
    ں
    2.69
    7
    2.66
    鹩
    2.42
     consultato
    2.38
    衕
    2.33
    과
    2.31
    u
    2.30
    Activations Density 0.013%

    No Known Activations