© 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. 54386
    Prev
    Next
    INDEX
    Explanations

    product units and types

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

    piece or set followed by item type

    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
    actéristiques
    0.46
    дати
    0.46
    ڡ
    0.45
    节日
    0.45
    枤
    0.44
    CLUDES
    0.44
     ወቅት
    0.44
     대한민국
    0.44
    வாகும்
    0.44
    вної
    0.43
    POSITIVE LOGITS
     High
    0.46
     Strategic
    0.46
     SWOT
    0.45
     ASEAN
    0.44
     Senior
    0.43
     Auto
    0.42
     Miao
    0.42
     Head
    0.41
     Jia
    0.41
     Z
    0.39
    Activations Density 0.022%

    No Known Activations