© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15539
    Prev
    Next
    INDEX
    Explanations

    transfer or migrate

    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
    melada
    -0.97
     resurgence
    -0.88
     installieren
    -0.84
     dosta
    -0.83
    安装
    -0.82
    安裝
    -0.81
    Restoration
    -0.77
     debuts
    -0.77
     nuevamente
    -0.76
    UPDATED
    -0.75
    POSITIVE LOGITS
     transfer
    1.10
     transferred
    1.05
     existing
    1.05
     त्या
    0.98
     TRANSFER
    0.96
    transfer
    0.95
    轉
    0.94
     Transition
    0.93
     chuyển
    0.93
    migrate
    0.92
    Activations Density 0.096%

    No Known Activations