© 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. 27221
    Prev
    Next
    INDEX
    Explanations

    race, lap, sets, duration

    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
     now
    -1.16
     from
    -0.96
     raya
    -0.91
     bandou
    -0.90
     components
    -0.90
    檢
    -0.90
     their
    -0.89
    Reviewed
    -0.87
     сих
    -0.87
     Conception
    -0.86
    POSITIVE LOGITS
     duration
    1.34
     Unterricht
    1.13
    dobe
    1.12
    indonesia
    1.09
     aantal
    1.02
     vetorial
    1.01
    iddhartha
    1.00
     Erinnerung
    1.00
    apartament
    0.98
    lysses
    0.98
    Activations Density 0.016%

    No Known Activations