© 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. 10-GEMMASCOPE-RES-131K
    7. 86518
    Prev
    Next
    INDEX
    Explanations

    list item markers

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

    The neuron flags isolated numeric list markers and section numbers (e.g. “2.”, “3.”) in documents.

    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
    </strong>
    -1.59
     
    -1.55
     four
    -1.45
    Shortly
    -1.38
     five
    -1.38
    After
    -1.37
    ++]=
    -1.36
    While
    -1.35
    తో
    -1.35
     three
    -1.34
    POSITIVE LOGITS
    ჱ
    1.80
    罍
    1.76
    Ộ
    1.73
     verhind
    1.68
     judicia
    1.67
     organisme
    1.67
    鹟
    1.65
    鳚
    1.59
     you
    1.56
     raiſ
    1.53
    Activations Density 0.026%

    No Known Activations