© 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. 64993
    Prev
    Next
    INDEX
    Explanations

    citations, numbers, section markers

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

    The neuron spotlights numbered section or item markers (e.g. section numbers and correction enumerations) in academic paper text.

    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
    Ư
    -0.86
    ),'
    -0.83
     americana
    -0.82
    不支持
    -0.82
     lät
    -0.81
    ZZA
    -0.81
     dibutuhkan
    -0.80
     nedir
    -0.79
     praktik
    -0.77
    Город
    -0.77
    POSITIVE LOGITS
     torrents
    0.83
    त्य
    0.83
     Cite
    0.82
     mooie
    0.78
    chism
    0.76
     ExecuteAsync
    0.76
     Pome
    0.73
    ′
    0.73
     asp
    0.73
     Abbe
    0.72
    Activations Density 0.008%

    No Known Activations