© 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. 34-GEMMASCOPE-RES-131K
    7. 57809
    Prev
    Next
    INDEX
    Explanations

    VC and university names

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

    This neuron pinpoints occurrences of the uppercase token “VC” (often in version strings or as the Visual C++ acronym).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     usarlo
    -0.88
    nicos
    -0.83
    NodeInfo
    -0.81
     contes
    -0.79
     Relocation
    -0.79
     appId
    -0.78
    🍸
    -0.78
     竹
    -0.74
     inond
    -0.73
    İR
    -0.71
    POSITIVE LOGITS
    Phen
    0.80
     Phen
    0.79
     VC
    0.73
    Hav
    0.73
    致
    0.72
     vc
    0.72
     lông
    0.71
     anúncios
    0.71
    Hab
    0.71
    计划
    0.71
    Activations Density 0.015%

    No Known Activations