© 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. 10-GEMMASCOPE-RES-131K
    7. 39179
    Prev
    Next
    INDEX
    Explanations

    poker

    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_10/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
     bala
    -1.27
    蹋
    -1.20
     zabaw
    -1.18
     surpl
    -1.16
     自転車
    -1.13
    我們的
    -1.13
     ambig
    -1.12
     Lumb
    -1.12
     africano
    -1.11
     celta
    -1.11
    POSITIVE LOGITS
     Mereka
    1.42
     ними
    1.36
     információ
    1.19
    
    1.19
    uuml
    1.16
     salieron
    1.16
     TO
    1.15
     gru
    1.14
     vieron
    1.13
    THEY
    1.12
    Activations Density 0.029%

    No Known Activations