© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181857
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite

    Application-Specific Functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ितीय
    0.49
     تشخیص
    0.46
     वैसे
    0.46
    轸
    0.45
    Model
    0.44
    絭
    0.44
    䒱
    0.43
    Render
    0.43
     ஊட்ட
    0.43
     ማድረግ
    0.42
    POSITIVE LOGITS
    اي
    0.55
     Agama
    0.47
    ضة
    0.46
    اج
    0.46
    ле
    0.45
     augue
    0.44
    اور
    0.44
    اعة
    0.43
    邊
    0.43
    內
    0.43
    Activations Density 0.000%

    No Known Activations