© 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. 70880
    Prev
    Next
    INDEX
    Explanations

    entity names and associated places

    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
    typically
    -0.95
    繼續
    -0.91
     typically
    -0.89
    変化
    -0.89
    results
    -0.85
     your
    -0.84
    normally
    -0.82
     rotación
    -0.81
     wyn
    -0.81
    évolution
    -0.81
    POSITIVE LOGITS
     revival
    2.13
     comeback
    1.82
     revived
    1.78
     revive
    1.77
     resurgence
    1.73
     revi
    1.62
     reborn
    1.56
     reviving
    1.56
     old
    1.48
     åter
    1.47
    Activations Density 0.177%

    No Known Activations