© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71973
    Prev
    Next
    INDEX
    Explanations

    emergency warnings and advisories

    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
    ionized
    -1.13
    orbit
    -1.13
    Yearly
    -1.06
    </h1>
    -1.05
    Annual
    -1.04
    gerichte
    -1.03
    Ouest
    -1.02
    ?
    -1.02
     étan
    -0.98
     câmbio
    -0.98
    POSITIVE LOGITS
     for
    1.54
     Thursday
    1.46
     Wednesday
    1.32
     comunicado
    1.30
     four
    1.30
    QtWidgets
    1.30
     advisory
    1.27
     Tuesday
    1.25
     warning
    1.22
     on
    1.21
    Activations Density 0.024%

    No Known Activations