© 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. 75123
    Prev
    Next
    INDEX
    Explanations

    first occurrence

    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
     ส์
    -1.62
     GETTING
    -1.56
     ſont
    -1.55
    ⛦
    -1.50
     ralenti
    -1.49
    鹩
    -1.48
     apropri
    -1.46
    嘮
    -1.43
     DEE
    -1.42
    annique
    -1.40
    POSITIVE LOGITS
     of
    2.88
     one
    2.39
     new
    2.20
     for
    2.14
     time
    1.99
     thing
    1.95
     from
    1.78
    </u>
    1.70
     in
    1.63
     we
    1.62
    Activations Density 0.049%

    No Known Activations