© 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. 10-GEMMASCOPE-RES-131K
    7. 86108
    Prev
    Next
    INDEX
    Explanations

    versioning or Visual Studio versions

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

    This neuron specifically detects occurrences of the token “VS,” as used (e.g. in Visual Studio version labels).

    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
    the
    -3.28
    1
    -2.83
    </em>
    -2.78
    
    -2.69
    ),
    -2.69
    ～。
    -2.58
    '))
    -2.56
     includes
    -2.55
    '])
    -2.48
    柃
    -2.45
    POSITIVE LOGITS
    秾
    3.06
    \
    2.67
     插画
    2.56
     dejected
    2.56
     Даль
    2.48
    蓠
    2.47
     intertw
    2.44
    了
    2.42
    秶
    2.41
    
    2.36
    Activations Density 0.011%

    No Known Activations