© 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. 34-GEMMASCOPE-RES-131K
    7. 33849
    Prev
    Next
    INDEX
    Explanations

    the [noun/adjective]

    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_34/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
    voer
    -1.52
    rably
    -1.36
    chery
    -1.34
    corrhi
    -1.30
    already
    -1.28
     menangis
    -1.27
    menü
    -1.27
    necessarily
    -1.25
    gleichen
    -1.24
     Mexique
    -1.23
    POSITIVE LOGITS
     reason
    2.28
     thing
    1.71
     main
    1.70
     most
    1.64
     total
    1.62
     duration
    1.55
     problem
    1.55
     said
    1.54
     other
    1.54
     also
    1.52
    Activations Density 0.127%

    No Known Activations