© 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-16K
    7. 13219
    Prev
    Next
    INDEX
    Explanations

    user manuals online

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

    shuttle nutrients to cells

    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_16k_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
    کند
    0.48
    利率
    0.47
    TERN
    0.46
     mercados
    0.46
    뀔
    0.44
    formes
    0.44
    ENSIVE
    0.43
    Produtos
    0.42
    鉅
    0.42
    巨
    0.42
    POSITIVE LOGITS
     đậu
    0.46
     hovering
    0.45
     Open
    0.45
     serpentine
    0.44
     अर
    0.43
     Johansson
    0.43
     Using
    0.43
     ઝ
    0.43
    म
    0.43
     транспорт
    0.42
    Activations Density 0.002%

    No Known Activations