© 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. 22-GEMMASCOPE-RES-131K
    7. 14216
    Prev
    Next
    INDEX
    Explanations

    markdown links and structure

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

    The neuron flags tokens used as structural markers in document outlines—especially section numbers, numbered heading labels, and related index or “foreword” markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Procedimento
    -1.20
     DESCRIP
    -1.19
     zeal
    -1.18
    aneity
    -1.16
    发布于
    -1.16
    的头
    -1.14
    Forme
    -1.11
     annon
    -1.09
     would
    -1.09
    ！！！！
    -1.08
    POSITIVE LOGITS
     to
    1.57
     how
    1.29
     changes
    1.23
    其他
    1.19
    </h2>
    1.16
     data
    1.13
     Why
    1.12
    ülerin
    1.11
    Koordinaten
    1.11
    </h3>
    1.06
    Activations Density 0.003%

    No Known Activations