© 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. 66779
    Prev
    Next
    INDEX
    Explanations

    data calculation and acquisition

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

    The neuron specializes in spotting quantitative and data‐related terms—words associated with measurements, data acquisition, analysis, and calculation.

    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
    薮
    -1.41
    меется
    -1.39
     responsable
    -1.30
    桧
    -1.26
     anlay
    -1.25
     trois
    -1.25
    endente
    -1.24
    唖
    -1.23
     uniforme
    -1.23
    觊
    -1.23
    POSITIVE LOGITS
     any
    1.61
    任何
    1.50
    由於
    1.40
     apoyar
    1.37
    #
    1.35
     liknande
    1.34
     pacchetto
    1.32
    因为
    1.27
    er
    1.27
     similar
    1.26
    Activations Density 0.391%

    No Known Activations