© 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. 34-GEMMASCOPE-RES-131K
    7. 90497
    Prev
    Next
    INDEX
    Explanations

    copyright notices and dates

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

    This neuron triggers on prominent metadata and identifier tokens—e.g. class or API names, section headings, boilerplate labels, dates, and other header‐style words.

    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
     Gemeins
    -0.70
     semblables
    -0.68
    িল
    -0.68
    изо
    -0.67
    Ade
    -0.67
    zysty
    -0.66
     liberar
    -0.65
    travail
    -0.65
    BOSS
    -0.65
    Ihr
    -0.65
    POSITIVE LOGITS
    AccessControl
    0.76
    meris
    0.68
     Notion
    0.66
     nurture
    0.66
     Aptitude
    0.65
    יי
    0.65
    DATE
    0.63
    нер
    0.63
     Soak
    0.63
    ї
    0.62
    Activations Density 0.068%

    No Known Activations