© 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. 39537
    Prev
    Next
    INDEX
    Explanations

    deal with vendors

    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
     our
    -1.18
    旋律
    -1.04
     we
    -0.98
     poliéster
    -0.98
    ruptcy
    -0.94
     ANCHE
    -0.92
    ulents
    -0.92
     ajoute
    -0.91
    醜
    -0.88
    軋
    -0.88
    POSITIVE LOGITS
    WillAppear
    1.32
    < 
    1.11
     contacts
    1.10
     الحصول
    1.07
    arpa
    1.05
     money
    1.04
    ák
    1.00
     劉
    1.00
    可靠
    1.00
    🪙
    1.00
    Activations Density 0.034%

    No Known Activations