© 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. 22178
    Prev
    Next
    INDEX
    Explanations

    end of clause or phrase

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

    questions and punctuation

    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
     ১৮
    0.39
     ၀
    0.39
     protein
    0.38
     প্রতিষ্ঠানের
    0.38
     එය
    0.37
     eprintln
    0.37
     ආහාර
    0.37
    নারায়ণ
    0.37
     উভয়
    0.36
     authors
    0.36
    POSITIVE LOGITS
    。
    0.64
    ؟
    0.62
    ။
    0.61
    ?!
    0.61
    !?
    0.60
    ！
    0.59
    ？
    0.58
    !!
    0.57
    !!!!
    0.55
    ։
    0.55
    Activations Density 0.001%

    No Known Activations