© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55861
    Prev
    Next
    INDEX
    Explanations

    academic paper structure

    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
    scriptsize
    -0.80
    Minh
    -0.79
    特性
    -0.77
     inner
    -0.77
    footnotesize
    -0.72
    UCN
    -0.72
    Avant
    -0.72
     tänker
    -0.70
     بیش
    -0.70
     ті
    -0.70
    POSITIVE LOGITS
     LARGE
    0.86
    ChrTalk
    0.83
     soph
    0.82
     setuptools
    0.79
    wohner
    0.79
    large
    0.78
    Huge
    0.77
    includegraphics
    0.77
     perpetrator
    0.77
    ète
    0.76
    Activations Density 0.003%

    No Known Activations