© 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. 68723
    Prev
    Next
    INDEX
    Explanations

    redirect old URLs

    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
     to
    -1.28
     if
    -1.23
     before
    -1.21
    祕
    -1.15
     could
    -1.14
     used
    -1.13
     may
    -1.12
     During
    -1.11
     would
    -1.10
     did
    -1.09
    POSITIVE LOGITS
    ՚
    1.48
    และ
    1.22
     până
    1.20
     automó
    1.19
     唯美
    1.19
     degrés
    1.16
     Logement
    1.16
    了
    1.16
    ระบบ
    1.13
     véhicules
    1.12
    Activations Density 0.050%

    No Known Activations