© 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. 9918
    Prev
    Next
    INDEX
    Explanations

    spark industry consolidation

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

    This neuron activates on words in title‐case headlines or section headings.

    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
    -2.30
     and
    -2.27
     or
    -2.02
     would
    -1.95
     there
    -1.91
     but
    -1.90
     during
    -1.80
     could
    -1.73
    when
    -1.68
     after
    -1.67
    POSITIVE LOGITS
     cuja
    1.96
     assorted
    1.88
    艄
    1.85
     conexiones
    1.82
     rígida
    1.81
     his
    1.80
     cujo
    1.79
    秾
    1.78
     ancla
    1.75
     disku
    1.74
    Activations Density 0.749%

    No Known Activations