© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44587
    Prev
    Next
    INDEX
    Explanations

    states or inclinations

    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
     in
    -2.13
     it
    -1.94
     by
    -1.63
     on
    -1.56
     there
    -1.44
    ’，
    -1.44
     time
    -1.38
     through
    -1.38
     went
    -1.36
     ofert
    -1.34
    POSITIVE LOGITS
     such
    1.65
     предыду
    1.52
     either
    1.50
     mehreren
    1.48
     других
    1.43
     peuvent
    1.38
     OVERVIEW
    1.31
     více
    1.28
     both
    1.27
     other
    1.27
    Activations Density 0.056%

    No Known Activations