© 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. 48085
    Prev
    Next
    INDEX
    Explanations

    strong positive adjectives

    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
     if
    -2.48
     with
    -2.39
     as
    -2.25
     for
    -2.23
     However
    -2.20
     at
    -2.14
     Although
    -2.14
     During
    -2.11
     While
    -2.11
     in
    -2.11
    POSITIVE LOGITS
     amazingly
    1.92
     wonderfully
    1.91
     insanely
    1.85
     acclaimed
    1.83
     quintessential
    1.80
     wondrous
    1.79
     ridiculously
    1.79
     delightfully
    1.77
     exceedingly
    1.77
     lauded
    1.76
    Activations Density 0.028%

    No Known Activations