© 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. 34-GEMMASCOPE-RES-131K
    7. 82586
    Prev
    Next
    INDEX
    Explanations

    composition

    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_34/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
     consentimiento
    -1.30
     gutes
    -1.19
     dotyczące
    -1.15
     coordination
    -1.13
    裥
    -1.11
     covering
    -1.09
     captivated
    -1.09
     economies
    -1.08
     connections
    -1.08
     设备
    -1.06
    POSITIVE LOGITS
     COMPOS
    1.42
     компози
    1.34
    Ком
    1.28
     Composition
    1.27
    COMPOS
    1.25
    inalg
    1.23
    al
    1.22
     COMPOSITION
    1.20
     Ком
    1.19
     Compos
    1.16
    Activations Density 0.022%

    No Known Activations