© 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. 3718
    Prev
    Next
    INDEX
    Explanations

    interrogative punctuation

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

    questions and follow-ups

    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
    س
    0.38
    ق
    0.34
    ز
    0.33
    ال
    0.32
    ه
    0.30
    اس
    0.30
    ت
    0.29
    رخ
    0.29
    ح
    0.29
    لات
    0.29
    POSITIVE LOGITS
    ?!?
    0.49
    ?!
    0.46
    ?
    0.43
    ?!?!
    0.38
    ?"
    0.32
     Yes
    0.31
    ?,
    0.31
     Or
    0.30
     หรือ
    0.30
    ?.
    0.30
    Activations Density 0.382%

    No Known Activations