© 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. 103594
    Prev
    Next
    INDEX
    Explanations

    author attribution

    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
    ll
    -1.25
    ’
    -1.20
    )
    -1.09
    鹮
    -1.05
    "
    -1.04
    味道
    -1.01
    will
    -0.96
    矗
    -0.95
    ")
    -0.93
     воздуха
    -0.92
    POSITIVE LOGITS
    author
    1.81
     Author
    1.78
    Author
    1.78
     author
    1.74
    itative
    1.73
     AUTHOR
    1.63
    authors
    1.55
    itarian
    1.35
     autor
    1.34
    ised
    1.30
    Activations Density 0.031%

    No Known Activations