© 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. 15-GEMMASCOPE-2-RES-16K
    7. 4584
    Prev
    Next
    INDEX
    Explanations

    lumbar support and stiff posture

    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
    FFEE
    1.47
     brewed
    1.23
    Coffee
    1.23
    Conference
    1.21
     커피
    1.20
    Printer
    1.20
     journe
    1.20
    🥯
    1.19
     printer
    1.19
    เมล
    1.16
    POSITIVE LOGITS
     Avila
    0.92
     Estrada
    0.92
     assistive
    0.92
     Hemsworth
    0.88
    дям
    0.88
     Arth
    0.87
     MOL
    0.86
     bioc
    0.86
     Bor
    0.84
     Reh
    0.84
    Activations Density 0.086%

    No Known Activations