© 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. 85032
    Prev
    Next
    INDEX
    Explanations

    capitalized word followed by noun

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

    This neuron detects the double-colon scope‐resolution token (“::”), as in namespace qualifiers.

    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
     которы
    -1.42
     какую
    -1.31
     tivesse
    -1.29
    o
    -1.28
    _
    -1.24
     katholischen
    -1.23
     zů
    -1.22
     $
    -1.21
     vali
    -1.21
     serait
    -1.20
    POSITIVE LOGITS
    푙
    1.54
    ޏ
    1.52
     kartą
    1.51
    ㈨
    1.50
     vesel
    1.48
     jedna
    1.48
     will
    1.45
    метры
    1.45
     času
    1.44
    zwald
    1.42
    Activations Density 0.000%

    No Known Activations