© 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. 10-GEMMASCOPE-RES-131K
    7. 39171
    Prev
    Next
    INDEX
    Explanations

    msgstr parsing

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

    The neuron identifies standalone, uppercase or title-case tokens that serve as section headers or metadata labels at the start of lines.

    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
    cadilly
    -2.27
    ichtete
    -2.14
     latter
    -2.02
    xnn
    -2.02
     apoi
    -2.00
     encompassing
    -1.97
     unruly
    -1.95
    tedì
    -1.93
     efekt
    -1.91
    tampa
    -1.91
    POSITIVE LOGITS
    ing
    3.27
    e
    2.89
    s
    2.78
    it
    2.39
    ar
    2.34
    t
    2.30
    u
    2.27
    a
    2.25
    ed
    2.20
    3
    2.14
    Activations Density 0.001%

    No Known Activations