© 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. 65505
    Prev
    Next
    INDEX
    Explanations

    code structure delimiting configurations

    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_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
    ⁡
    -1.20
    горя
    -1.14
     then
    -1.09
     ſ
    -1.03
     steder
    -1.02
     CHtml
    -1.00
     minutter
    -1.00
    āci
    -1.00
     ۱۹
    -0.99
     Seigneur
    -0.99
    POSITIVE LOGITS
    مقال
    1.06
    Kako
    1.01
    Resultados
    1.01
    Artigo
    1.00
     that
    0.98
    Ilustra
    0.98
     These
    0.97
    Opin
    0.97
     if
    0.96
    でもない
    0.96
    Activations Density 0.015%

    No Known Activations