© 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. 10-GEMMASCOPE-RES-131K
    7. 42629
    Prev
    Next
    INDEX
    Explanations

    software extensions and plugins

    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_10/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
     quien
    -1.40
    笈
    -1.36
    Not
    -1.30
    Though
    -1.27
    However
    -1.23
    mbros
    -1.22
    Although
    -1.20
     coupled
    -1.20
     ролях
    -1.18
    日在
    -1.16
    POSITIVE LOGITS
     soportes
    1.38
     frequentemente
    1.38
     such
    1.34
    riy
    1.28
    鎢
    1.26
    鮰
    1.25
     generando
    1.23
    FECTION
    1.21
     misterioso
    1.21
     Auftritt
    1.21
    Activations Density 0.184%

    No Known Activations