© 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. 75298
    Prev
    Next
    INDEX
    Explanations

    Go import statements

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

    The neuron is keyed to the kinds of comment‐ and metadata‐markers you see at the tops of source files—things like “//”, “%”, “/**”, license years, copyright notices, usage headings, and the surrounding quote delimiters.

    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
    傚
    -2.09
     this
    -2.02
    iramente
    -2.00
     that
    -1.92
    
    -1.91
    佷
    -1.85
    fordshire
    -1.84
    девушка
    -1.82
     וכן
    -1.80
    ⛦
    -1.80
    POSITIVE LOGITS
    </strong>
    2.27
    )
    2.09
    a
    1.98
    '
    1.93
    i
    1.88
    e
    1.88
    to
    1.87
    is
    1.84
     \
    1.80
    ,
    1.79
    Activations Density 52.342%

    No Known Activations