© 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. 36486
    Prev
    Next
    INDEX
    Explanations

    events and dates

    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
     our
    -1.72
     we
    -1.63
    tyimages
    -1.48
    我们
    -1.43
     consectetur
    -1.36
    🪙
    -1.32
    albeit
    -1.26
    Ģ
    -1.25
     protože
    -1.24
    isman
    -1.23
    POSITIVE LOGITS
     will
    1.95
     at
    1.66
     with
    1.63
     also
    1.44
     reportedly
    1.32
     eight
    1.27
     five
    1.27
     during
    1.26
     Atenas
    1.25
     provide
    1.24
    Activations Density 0.059%

    No Known Activations