© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2404
    Prev
    Next
    INDEX
    Explanations

    exclamations and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.29
    ти
    0.28
    ق
    0.27
    ید
    0.27
    ین
    0.26
    ای
    0.25
    الع
    0.25
    تی
    0.25
    ہ
    0.24
    да
    0.23
    POSITIVE LOGITS
    0.27
     waarbij
    0.25
     procedente
    0.24
    rante
    0.24
    aing
    0.24
    on
    0.24
     από
    0.24
     legt
    0.23
     ότι
    0.23
     wodurch
    0.23
    Activations Density 0.011%

    No Known Activations