© 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. 40605
    Prev
    Next
    INDEX
    Explanations

    question words followed by auxiliary verbs

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

    questions starting with What

    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
    あなたは
    0.46
     المصطلح
    0.43
     هذا
    0.42
    आपने
    0.41
     iyong
    0.41
     organizar
    0.41
     utiliser
    0.40
    ဤ
    0.40
    你自己
    0.40
     choisir
    0.39
    POSITIVE LOGITS
     erster
    0.45
     Đức
    0.44
     первое
    0.43
     Araújo
    0.43
     πρώτη
    0.42
     tantal
    0.42
     Zwei
    0.42
     eerste
    0.41
    igil
    0.41
    adt
    0.40
    Activations Density 0.006%

    No Known Activations