© 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. 75138
    Prev
    Next
    INDEX
    Explanations

    SEMA Show, Xbox, Michigan Supreme Court

    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
     السياس
    -1.45
    𝒙
    -1.42
    Når
    -1.26
    wirtschaft
    -1.23
     نہیں
    -1.22
    När
    -1.18
    ଂ
    -1.17
     lópez
    -1.15
     anonim
    -1.14
    
    -1.13
    POSITIVE LOGITS
     they
    1.45
     everything
    1.30
    \
    1.22
    雑貨
    1.20
     changes
    1.17
    tando
    1.15
     but
    1.13
     how
    1.10
     who
    1.09
     we
    1.09
    Activations Density 0.009%

    No Known Activations