© 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. 10-GEMMASCOPE-RES-131K
    4. 65008
    Prev
    Next
    INDEX
    Explanations

    http, https, Backyard, Match, LIVE

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

    The neuron activates on document section headings or metadata labels ending with a colon (e.g. “Sort:”, “Job Description:”, “Source:”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     decidido
    -2.03
     then
    -2.03
     motocicletas
    -1.70
    وضح
    -1.66
    guigu
    -1.66
    tissu
    -1.66
     brilhante
    -1.61
     enfrenta
    -1.61
     because
    -1.59
     souhaite
    -1.59
    POSITIVE LOGITS
    er
    1.85
    b
    1.84
    these
    1.76
    ла
    1.73
    A
    1.72
    from
    1.70
    9
    1.67
    re
    1.66
    These
    1.65
     estos
    1.65
    Activations Density 0.021%

    No Known Activations