© 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. 7852
    Prev
    Next
    INDEX
    Explanations

    words like "thank you"

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

    abstract concepts and properties

    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
    <strong>
    0.45
    to
    0.42
    idental
    0.40
     inset
    0.40
    <b>
    0.39
     Storage
    0.39
    uring
    0.38
     storage
    0.38
     context
    0.37
    barcode
    0.37
    POSITIVE LOGITS
    婍
    0.49
    作る
    0.44
    اہد
    0.43
    フィ
    0.43
     personalmente
    0.43
     ಅವರು
    0.42
     personales
    0.42
     chết
    0.42
    पुरुष
    0.42
     पुरुष
    0.42
    Activations Density 0.001%

    No Known Activations