© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103929
    Prev
    Next
    INDEX
    Explanations

    section markers like {#sect}

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

    The neuron is keyed to structural markup tokens (section/anchor markers, footnote or reference symbols, and other document-structure tags).

    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
    gments
    -0.79
     Zone
    -0.74
    gonz
    -0.72
     ring
    -0.71
    Zone
    -0.70
    四
    -0.70
     loop
    -0.69
    geon
    -0.68
    paigns
    -0.68
     Zones
    -0.67
    POSITIVE LOGITS
     découvrir
    0.89
    Ukra
    0.83
    Nora
    0.81
    Hå
    0.81
     arriver
    0.81
    CONTEN
    0.80
    Comunic
    0.79
    Toul
    0.79
    ANTAGES
    0.78
    Früh
    0.78
    Activations Density 0.027%

    No Known Activations