© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66496
    Prev
    Next
    INDEX
    Explanations

    specific, exact, precise, true

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

    This neuron responds to qualifier adjectives that emphasize precision or specificity (e.g. “exact,” “relative,” “specific,” “current,” “true,” “precise,” etc.).

    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
    があるので
    -2.11
     maig
    -2.00
    และ
    -1.93
    ࿊
    -1.88
    もあるので
    -1.81
     MAKING
    -1.80
     BEAUT
    -1.80
     唯美
    -1.77
    aneity
    -1.73
    があると
    -1.73
    POSITIVE LOGITS
     uses
    1.98
     characteristics
    1.90
     incredible
    1.88
     high
    1.81
     eight
    1.77
     enormous
    1.77
     information
    1.73
     increases
    1.73
     innovative
    1.72
     extraordinary
    1.72
    Activations Density 0.072%

    No Known Activations