© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105634
    Prev
    Next
    INDEX
    Explanations

    other objects

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

    The neuron fires on general-category nouns naming collections of things or substances (e.g. “materials,” “information,” “drugs,” “ingredients,” “devices,” “products,” “objects”).

    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
     there
    -1.64
    There
    -1.40
     розпові
    -1.34
    娯
    -1.34
     ребё
    -1.34
    震惊
    -1.33
    Kemudian
    -1.27
    كتشاف
    -1.26
    Selanjutnya
    -1.24
     four
    -1.23
    POSITIVE LOGITS
     "
    1.91
     of
    1.75
     will
    1.68
     quando
    1.54
     '
    1.41
     gibi
    1.41
     similar
    1.40
    因为
    1.40
     comienzos
    1.38
     др
    1.36
    Activations Density 0.080%

    No Known Activations