© 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. 22-GEMMASCOPE-RES-131K
    7. 68891
    Prev
    Next
    INDEX
    Explanations

    companies or organisations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ‌هایی
    -0.90
     weißt
    -0.85
    thio
    -0.85
    뉴
    -0.84
     Bewußt
    -0.83
     שלהם
    -0.83
     veille
    -0.82
     платье
    -0.82
     prière
    -0.81
     bekom
    -0.81
    POSITIVE LOGITS
     companies
    1.22
     подоб
    1.01
     like
    1.00
    inguém
    0.93
    iconCls
    0.91
     company
    0.91
     pelajar
    0.90
     提示
    0.90
     perusahaan
    0.88
     wanita
    0.88
    Activations Density 0.087%

    No Known Activations