© 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. 22-GEMMASCOPE-RES-131K
    7. 65901
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
     (
    -1.30
     $
    -1.26
     sometimes
    -1.16
     provide
    -1.12
     value
    -1.12
    шила
    -1.11
     often
    -1.05
     usually
    -1.05
     applications
    -1.01
     equation
    -1.01
    POSITIVE LOGITS
    从来没有
    1.25
     început
    1.20
     sicuro
    1.16
     meravigli
    1.11
     cinturón
    1.10
     disebutkan
    1.07
     göm
    1.07
     piacevole
    1.06
     pidió
    1.05
     nimmer
    1.04
    Activations Density 0.005%

    No Known Activations