© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10037
    Prev
    Next
    INDEX
    Explanations

    question punctuation and particles

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

    question marks or interrogatives

    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_40_width_16k_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
     Transitional
    0.43
    **,
    0.39
     Scenic
    0.39
    .):
    0.38
    ┑
    0.38
     อย
    0.37
     Lagrangian
    0.36
    일을
    0.35
    ılıyor
    0.35
     ব্রিজ
    0.35
    POSITIVE LOGITS
     ?
    1.02
     ?"
    0.81
    吗
    0.81
    嗎
    0.79
     ?”
    0.71
     ?$
    0.61
     ?",
    0.61
     ؟
    0.61
    ไหม
    0.60
    了吗
    0.56
    Activations Density 0.006%

    No Known Activations