© 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. 129219
    Prev
    Next
    INDEX
    Explanations

    virtual objects and concepts

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

    The neuron is highly sensitive to nouns that typically follow the adjective “virtual,” i.e. key product or service names used in “virtual X” constructions.

    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
     niektor
    -1.40
     býval
    -1.39
     yaptığı
    -1.37
     princesas
    -1.35
     ním
    -1.34
     viszont
    -1.31
     cayó
    -1.29
     nourriture
    -1.27
     ťaž
    -1.27
     ženy
    -1.27
    POSITIVE LOGITS
     virtual
    1.77
    virtual
    1.52
     They
    1.36
     Virtual
    1.35
     of
    1.32
     VIRTUAL
    1.30
    Virtual
    1.30
    ”
    1.26
     will
    1.23
    虚拟
    1.22
    Activations Density 0.072%

    No Known Activations