© 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. 130911
    Prev
    Next
    INDEX
    Explanations

    the followed by a noun

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

    The neuron strongly responds to the very first content word at the start of a new section or sentence.

    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
    ]]=
    -1.77
     الأخرى
    -1.60
    ।
    -1.55
    洐
    -1.55
    倧
    -1.52
    ricos
    -1.52
    (!__
    -1.51
    omeric
    -1.48
    чен
    -1.46
    掬
    -1.46
    POSITIVE LOGITS
     the
    2.59
    ’,
    1.70
    on
    1.62
    er
    1.58
    當時
    1.54
    o
    1.52
     each
    1.49
    ’
    1.41
    in
    1.41
    ,’
    1.39
    Activations Density 0.001%

    No Known Activations