© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127822
    Prev
    Next
    INDEX
    Explanations

    Democracy Agenda

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

    The neuron activates on code examples or code blocks (e.g. content inside `<code>` tags or fenced code snippets).

    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
    \
    -2.14
    “
    -2.11
    ?”
    -2.06
    LARATION
    -2.03
     to
    -1.95
    '].'
    -1.88
    </strong>
    -1.81
     мысль
    -1.77
     \
    -1.73
    ﺲ
    -1.71
    POSITIVE LOGITS
     These
    2.47
    冢
    2.00
    [
    1.95
    是非常
    1.91
    Because
    1.87
     versucht
    1.87
    Their
    1.86
    They
    1.86
    I
    1.82
    したが
    1.80
    Activations Density 0.001%

    No Known Activations