© 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. 10-GEMMASCOPE-RES-131K
    7. 84963
    Prev
    Next
    INDEX
    Explanations

    parentheses around abbreviations

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

    The neuron responds to numerical values and quantitative measurements in the text (e.g. numbers with units or numerical annotations).

    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
    rógeno
    -1.76
    /***/
    -1.70
    "
    -1.63
    ￡
    -1.59
    didSet
    -1.57
     }));
    -1.50
    uliert
    -1.48
     gev
    -1.48
    Either
    -1.46
     groen
    -1.46
    POSITIVE LOGITS
     are
    2.45
     should
    1.80
     will
    1.77
     berharap
    1.73
     on
    1.73
     verrez
    1.72
     they
    1.72
     there
    1.70
     it
    1.65
     hoping
    1.64
    Activations Density 0.115%

    No Known Activations