© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4928
    Prev
    Next
    INDEX
    Explanations

    plate or plates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    薫
    1.36
    향
    1.35
     cinnamon
    1.31
     campañas
    1.27
     campaña
    1.24
     Cinnamon
    1.22
    缭
    1.21
     향
    1.21
    뿜
    1.20
    startswith
    1.17
    POSITIVE LOGITS
     Mee
    1.59
     PLATE
    1.59
     plates
    1.57
     Tarr
    1.56
     Plates
    1.56
     Plate
    1.56
    plates
    1.54
     tect
    1.54
     Conver
    1.53
     Emery
    1.51
    Activations Density 0.018%

    No Known Activations