© 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. 10998
    Prev
    Next
    INDEX
    Explanations

    air, defense, and vehicles

    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
    ’
    -1.16
     those
    -1.12
     gdyż
    -1.10
    -
    -1.07
     ”
    -1.01
     zra
    -1.01
     sèche
    -0.99
     highly
    -0.99
    為に
    -0.98
     jih
    -0.96
    POSITIVE LOGITS
     Obtén
    1.05
    ！"
    1.03
     ไม่
    1.01
     تنظ
    0.97
    datable
    0.92
    eterangan
    0.92
    lossen
    0.91
     ----
    0.89
     utilisons
    0.88
     ketika
    0.88
    Activations Density 0.090%

    No Known Activations