© 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. 131055
    Prev
    Next
    INDEX
    Explanations

    trailer teaser footage

    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
    すすめ
    -1.20
     when
    -1.11
     lorsqu
    -1.09
    ទ
    -1.08
     quando
    -1.06
    ώ
    -1.05
    bb
    -1.05
     cuando
    -1.04
     documented
    -1.04
     health
    -1.03
    POSITIVE LOGITS
     preview
    1.64
     brille
    1.38
    ivät
    1.27
     distinguer
    1.23
     teaser
    1.21
     капю
    1.20
    презента
    1.20
    teaser
    1.19
     soleil
    1.19
    ̬
    1.17
    Activations Density 0.047%

    No Known Activations