© 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. 22-GEMMASCOPE-RES-131K
    4. 12474
    Prev
    Next
    INDEX
    Explanations

    SPIR-V shaders

    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
     while
    -2.17
     when
    -2.06
     if
    -1.98
     after
    -1.95
     that
    -1.79
     using
    -1.61
     because
    -1.59
     during
    -1.59
     before
    -1.55
     While
    -1.55
    POSITIVE LOGITS
    ཿ
    1.46
     laquelle
    1.34
     creer
    1.28
     strukt
    1.27
     ouvert
    1.27
    なかな
    1.27
     avantages
    1.26
    様な
    1.26
    方に
    1.23
     impresionantes
    1.23
    Activations Density 0.003%

    No Known Activations