© 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. 11241
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

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

    opening curly braces in code that define the start of a code block or scope.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron selectively fires on the “get{” token pattern, i.e. the opening brace of a C# property getter.

    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
     what
    -2.33
     invigor
    -2.22
     every
    -2.16
     unrelenting
    -2.08
     from
    -2.02
     Since
    -1.98
     provide
    -1.92
     If
    -1.90
     because
    -1.90
     by
    -1.90
    POSITIVE LOGITS
     ส์
    2.73
    ᷆
    2.33
    atized
    2.33
    쫑
    2.31
    actéristi
    2.20
    糁
    2.17
     delightfully
    2.16
    튿
    2.16
    莛
    2.14
    </h2>
    2.06
    Activations Density 0.009%

    No Known Activations