© 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. 79902
    Prev
    Next
    INDEX
    Explanations

    ongoing wars and events

    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
     of
    -1.16
     a
    -1.05
    mycompany
    -0.93
     love
    -0.90
     modern
    -0.90
    <>());
    -0.89
     YOU
    -0.87
     tradiciones
    -0.87
     natural
    -0.84
    hearsal
    -0.84
    POSITIVE LOGITS
     continues
    1.31
     continuing
    1.29
     ongoing
    1.23
     weiterhin
    1.23
     continue
    1.20
    一直在
    1.11
    最近は
    1.09
     continued
    1.09
    继续
    1.09
     randon
    1.08
    Activations Density 0.088%

    No Known Activations