© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72692
    Prev
    Next
    INDEX
    Explanations

    Xilinx programmable devices

    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
     its
    -1.38
    不得不说
    -1.37
     když
    -1.34
     portuguesa
    -1.32
    可以选择
    -1.30
     повре
    -1.30
     continued
    -1.25
    ação
    -1.24
     boton
    -1.24
    おはようございます
    -1.21
    POSITIVE LOGITS
     ayak
    1.27
    Owl
    1.22
    apped
    1.21
     also
    1.20
    まって
    1.15
    EDAD
    1.14
     äm
    1.14
     acceptez
    1.13
     ganadores
    1.13
    ICAN
    1.12
    Activations Density 0.036%

    No Known Activations