© 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. 11135
    Prev
    Next
    INDEX
    Explanations

    api endpoints and urls

    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
    但是在
    -1.25
    ymbol
    -1.23
     automne
    -1.19
    但却
    -1.18
     vorige
    -1.18
    但在
    -1.16
     seleção
    -1.16
     ilustracji
    -1.15
    même
    -1.14
    ariConfig
    -1.14
    POSITIVE LOGITS
    get
    1.34
     then
    1.27
    ViewChild
    1.26
    Then
    1.24
     them
    1.21
    Every
    1.21
    Both
    1.14
     of
    1.14
    Two
    1.13
     nunc
    1.11
    Activations Density 0.003%

    No Known Activations