© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1686
    Prev
    Next
    INDEX
    Explanations

    gardens and outdoor spaces

    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_15_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
    壅
    1.44
     hábito
    1.41
    orama
    1.38
    ieuses
    1.35
    刷新
    1.35
    훑
    1.33
    واز
    1.32
    Ordine
    1.31
    珉
    1.31
    让我
    1.31
    POSITIVE LOGITS
     Seeds
    1.54
     pasture
    1.53
     tractors
    1.53
     Deere
    1.50
     mascotas
    1.46
     carport
    1.45
    🚜
    1.44
     gardener
    1.44
    畑
    1.40
     Horses
    1.40
    Activations Density 0.367%

    No Known Activations