© 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. 111184
    Prev
    Next
    INDEX
    Explanations

    source: entity names

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

    The neuron flags document metadata lines that cite a source or reference by name followed by a number (e.g. “Source: 336”).

    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
     "
    -1.95
     
    -1.80
    tifications
    -1.62
     ."
    -1.59
     caramel
    -1.56
     används
    -1.55
    もありました
    -1.54
    銈
    -1.52
     obscured
    -1.48
     precioso
    -1.48
    POSITIVE LOGITS
     their
    1.92
     these
    1.88
     from
    1.74
    യും
    1.67
     gigi
    1.67
     before
    1.63
     Wartawan
    1.63
    te
    1.63
     malang
    1.63
    hadores
    1.62
    Activations Density 0.006%

    No Known Activations