© 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. 71535
    Prev
    Next
    INDEX
    Explanations

    Australia National, Hour Traffic, Family Carer

    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
     majestic
    -1.23
     REALLY
    -1.22
     insanely
    -1.21
     mediocre
    -1.20
    を行います
    -1.16
     unbelievably
    -1.15
     revered
    -1.14
    を目指す
    -1.12
     gigantic
    -1.12
     AssemblyVersion
    -1.12
    POSITIVE LOGITS
     at
    1.47
     using
    1.30
     allowing
    1.27
     during
    1.26
     despite
    1.20
     only
    1.16
     when
    1.13
     includes
    1.13
     contextLoads
    1.11
     allows
    1.10
    Activations Density 0.080%

    No Known Activations