© 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. 44947
    Prev
    Next
    INDEX
    Explanations

    booklet of poetry

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

    model providing explanations

    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
    মিস্ট
    0.33
    的的
    0.30
    সরকারী
    0.29
     Direito
    0.28
    咊
    0.28
    ర్రీ
    0.28
     hath
    0.28
     ith
    0.28
     বিলম্ব
    0.27
    াস্থ্য
    0.27
    POSITIVE LOGITS
    1
    0.35
    .
    0.33
    5
    0.32
    7
    0.31
    IE
    0.31
     [
    0.30
    0.30
     and
    0.29
     A
    0.29
    4
    0.29
    Activations Density 0.159%

    No Known Activations