© 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. 34-GEMMASCOPE-RES-131K
    7. 75414
    Prev
    Next
    INDEX
    Explanations

    abstract: abstract: abstract: abstract: Stable Isotope Potentiometric

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

    structural elements in markup or technical documents, particularly focusing on XML, HTML, and abstract sections.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric tokens—especially version numbers and digits—within technical markup or metadata declarations.

    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
     Klasse
    -0.96
    ி
    -0.90
    Explorer
    -0.79
     kunjungan
    -0.79
     ...)
    -0.79
    SqlServer
    -0.78
     \\[
    -0.78
    见
    -0.78
     undangan
    -0.77
     penulis
    -0.77
    POSITIVE LOGITS
    pgterms
    1.08
     rdf
    0.94
    걍
    0.88
     erfolgreiche
    0.88
    rdf
    0.87
    ռ
    0.85
     geboten
    0.84
     actuales
    0.84
    糰
    0.81
     RDF
    0.81
    Activations Density 0.013%

    No Known Activations