© 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. 66330
    Prev
    Next
    INDEX
    Explanations

    hot drinks and food

    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
     you
    -1.32
     Appetit
    -1.12
     other
    -1.00
    IBU
    -0.98
    IFI
    -0.96
     тър
    -0.94
    other
    -0.91
    かというと
    -0.90
     sondern
    -0.89
     strconv
    -0.89
    POSITIVE LOGITS
    )];
    1.43
     drink
    1.30
     {}
    1.25
     lunch
    1.20
     erbjuder
    1.20
    '));
    1.18
     élas
    1.14
    xhttp
    1.14
     reichlich
    1.14
     some
    1.13
    Activations Density 0.031%

    No Known Activations