© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99518
    Prev
    Next
    INDEX
    Explanations

    skills or knowledge needed

    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
    Кто
    -1.19
    Siapa
    -1.18
    關於
    -1.04
    Makanan
    -0.99
    什么
    -0.98
    Werbung
    -0.98
    Selain
    -0.97
    Spesifikasi
    -0.96
     nytt
    -0.96
    ૬
    -0.95
    POSITIVE LOGITS
     necessary
    3.13
     needed
    2.78
     that
    2.38
    necessary
    1.84
     to
    1.77
     necesario
    1.73
     you
    1.71
     notwendig
    1.65
     it
    1.64
     potrebné
    1.57
    Activations Density 0.039%

    No Known Activations