© 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. 80648
    Prev
    Next
    INDEX
    Explanations

    Q&A format

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

    This neuron fires on Chinese words referring to software updates, fixes, improvements, or related change notices.

    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
     of
    -2.22
     there
    -2.00
     you
    -1.67
     poursuit
    -1.65
     along
    -1.59
     the
    -1.58
     your
    -1.55
     it
    -1.55
     are
    -1.54
    тература
    -1.51
    POSITIVE LOGITS
    4
    2.33
    5
    2.28
    6
    2.23
    3
    2.16
    0
    2.05
    7
    1.91
    2
    1.85
    9
    1.80
    8
    1.77
     four
    1.77
    Activations Density 0.008%

    No Known Activations