© 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. 80588
    Prev
    Next
    INDEX
    Explanations

    roles of a thing

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

    The neuron fires on numeric measurements (especially decimal‐point values) appearing in scientific text.

    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
    because
    -1.48
     étr
    -1.36
     karena
    -1.34
    كر
    -1.33
    よって
    -1.23
     ,
    -1.23
     daging
    -1.21
    分ほど
    -1.19
     haline
    -1.18
    waniem
    -1.17
    POSITIVE LOGITS
    多种
    1.37
     exportación
    1.29
     soprattutto
    1.27
     both
    1.27
     renovación
    1.26
     разные
    1.25
     modificación
    1.25
     operación
    1.25
     reunión
    1.24
     productividad
    1.23
    Activations Density 0.202%

    No Known Activations