© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 99972
    Prev
    Next
    INDEX
    Explanations

    on, from, between followed by articles

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

    The neuron detects the characteristic “patent-ese” linking and enumerating terms and symbols (e.g. “includes,” “disposed,” “comprising,” colons, semicolons, numbered items, and prepositions like “in”/“on”) used to list and define technical components.

    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
     dianggap
    -0.98
    なども
    -0.95
     таких
    -0.92
     Ngoài
    -0.91
    UBER
    -0.91
    Listed
    -0.90
    größern
    -0.90
     dôle
    -0.89
     möjlighet
    -0.88
     trouvait
    -0.88
    POSITIVE LOGITS
     a
    2.27
     said
    1.88
     first
    1.71
     an
    1.48
     one
    1.32
     second
    1.32
    少なくとも
    1.23
     only
    1.17
    first
    1.13
     atleast
    1.09
    Activations Density 0.448%

    No Known Activations