© 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. 34-GEMMASCOPE-RES-131K
    7. 2555
    Prev
    Next
    INDEX
    Explanations

    class/object method calls

    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
     ön
    -0.96
     этих
    -0.95
     hè
    -0.94
    eding
    -0.89
    も同じ
    -0.88
    多人
    -0.88
    ¸
    -0.85
     în
    -0.85
     pontos
    -0.84
     costos
    -0.83
    POSITIVE LOGITS
    DPA
    0.96
    😭😭
    0.96
     concentra
    0.95
    ❤️❤️❤️
    0.94
    ✨✨
    0.93
    ✋
    0.93
    🤣🤣🤣
    0.93
     Jumat
    0.93
     آقای
    0.92
     alpina
    0.91
    Activations Density 0.011%

    No Known Activations