© 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. 68919
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    :{
    -1.33
    に戻
    -1.02
    ちな
    -1.00
     about
    -1.00
    ございません
    -0.98
     brinquedos
    -0.98
    ÍSTICAS
    -0.98
    癥
    -0.98
    :!
    -0.97
    ({
    -0.97
    POSITIVE LOGITS
    饅
    1.38
    المصادر
    1.23
    海苔
    1.18
    Vegeta
    1.16
    Mosa
    1.16
    Sami
    1.13
    ジナル
    1.13
     assortment
    1.13
    礎
    1.11
    iciado
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.