© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71820
    Prev
    Next
    INDEX
    Explanations

    walk sensor, walk test, walk of

    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_10/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
     \
    -2.45
     disregarding
    -2.06
    .
    -2.03
    ですが
    -2.00
    Specifically
    -2.00
     –
    -1.98
            
    -1.94
     has
    -1.90
    蹙
    -1.86
    What
    -1.85
    POSITIVE LOGITS
    Sudah
    2.36
     heartache
    2.30
     burdensome
    2.13
     sarcasm
    2.05
     sultry
    2.02
    Wann
    2.02
     murky
    2.00
     يعرف
    1.99
     dependable
    1.97
     tiresome
    1.97
    Activations Density 0.009%

    No Known Activations