© 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. 22-GEMMASCOPE-RES-131K
    7. 86
    Prev
    Next
    INDEX
    Explanations

    resistors and resistance

    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
     lae
    -1.16
    plication
    -1.14
    گزاری
    -1.13
    頜
    -1.12
     struk
    -1.11
     superiore
    -1.11
     بشكل
    -1.09
    葙
    -1.06
    ichord
    -1.06
    ">“
    -1.05
    POSITIVE LOGITS
     with
    1.38
     this
    1.28
     attesa
    1.23
     since
    1.23
    []={
    1.21
     種類
    1.17
     tudom
    1.09
     izdel
    1.09
     törvény
    1.07
     Deber
    1.07
    Activations Density 0.038%

    No Known Activations