© 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. 34-GEMMASCOPE-RES-131K
    7. 49759
    Prev
    Next
    INDEX
    Explanations

    API and documentation reference

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

    The neuron fires on documentation‐page header metadata—things like “API” titles, version numbers, “Generated by javadoc,” and other HTML doc header elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    author
    -0.88
    ينة
    -0.86
     Durchführung
    -0.80
     setup
    -0.80
    arParams
    -0.79
     author
    -0.79
     prakty
    -0.79
    isDebugEnabled
    -0.77
    InitVars
    -0.76
    layout
    -0.76
    POSITIVE LOGITS
     reference
    2.17
    reference
    1.88
     documentation
    1.84
     Reference
    1.81
     REFERENCE
    1.65
    Reference
    1.65
    REFERENCE
    1.64
     API
    1.54
    Referencia
    1.41
    documentation
    1.38
    Activations Density 0.145%

    No Known Activations