© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72288
    Prev
    Next
    INDEX
    Explanations

    documentation for components and literature

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

    The neuron fires on documentation-style metadata or tag tokens (e.g. attribute names, section headings, and other code/doc markup labels).

    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
     Campeonato
    -1.03
    czenia
    -1.00
    IVOS
    -0.98
    にほんブログ村
    -0.96
    tiap
    -0.96
    ıca
    -0.95
     ketika
    -0.94
     καλύτε
    -0.94
    imbang
    -0.94
     Distrito
    -0.94
    POSITIVE LOGITS
     geschieht
    1.04
    ?
    1.02
    <.
    1.02
    ্ষ
    1.00
     男性
    1.00
     function
    0.96
     expresar
    0.93
     preguntar
    0.93
    辦法
    0.91
     vorigen
    0.91
    Activations Density 0.003%

    No Known Activations