© 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. 42408
    Prev
    Next
    INDEX
    Explanations

    calculated statistics

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

    This neuron detects numerical data reporting, especially statistical or computed values (e.g. “calculated,” “computed,” and the numbers that follow).

    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
    
    -2.27
    鹛
    -2.19
    </h1>
    -2.16
     ними
    -1.98
     که
    -1.98
    тата
    -1.98
    MenuInflater
    -1.92
     connus
    -1.89
    </strong>
    -1.88
     вр
    -1.85
    POSITIVE LOGITS
     calculated
    2.33
     computed
    2.14
    '
    2.05
     contributing
    1.95
     ツリー
    1.90
    .
    1.90
     Allgemeinen
    1.88
    猡
    1.84
     взгляд
    1.79
    calculated
    1.77
    Activations Density 0.010%

    No Known Activations