© 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. 23874
    Prev
    Next
    INDEX
    Explanations

    delegate and setting properties

    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
    WL
    -0.86
    Controller
    -0.81
    ľov
    -0.79
    efeated
    -0.78
     *>(
    -0.78
    uasion
    -0.77
    ]}\
    -0.76
    LOO
    -0.75
    NGL
    -0.75
    enchymal
    -0.75
    POSITIVE LOGITS
     delegate
    0.97
    delegate
    0.95
    攻擊
    0.78
    明显
    0.78
     delegates
    0.78
     modus
    0.77
     Delegates
    0.75
     builds
    0.74
     digs
    0.73
    ulfate
    0.73
    Activations Density 0.046%

    No Known Activations