© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38466
    Prev
    Next
    INDEX
    Explanations

    software libraries and frameworks

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

    The neuron fires on the names or identifiers of software libraries, modules, or projects (e.g. “networkx,” “commons.math,” “summernote,” “glm,” “OpenSSL,” “FreeType”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to software libraries, frameworks, or technical project names in source code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    names of software libraries or project/module identifiers—often acronyms—in code headers, imports, and documentation.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     нажмите
    -1.20
     ekolog
    -1.15
     in
    -1.15
     libras
    -1.13
     so
    -1.09
    ₋
    -1.09
     veren
    -1.09
    🗑
    -1.07
    oires
    -1.05
    kese
    -1.05
    POSITIVE LOGITS
    有过
    1.27
    بیش
    1.24
    에서는
    1.20
     mentre
    1.19
     ウール
    1.17
    Bereich
    1.15
     aprobado
    1.13
     リブ
    1.12
    Principales
    1.12
     comportamento
    1.11
    Activations Density 0.079%

    No Known Activations