© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11533
    Prev
    Next
    INDEX
    Explanations

    combination and paired

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ার্টমেন্ট
    2.76
    enchymal
    2.71
    י
    2.69
    쏠
    2.64
    екст
    2.54
    惕
    2.52
    डोर
    2.51
     Check
    2.50
    evice
    2.49
    ==============]
    2.47
    POSITIVE LOGITS
    ac
    2.64
    ade
    2.62
     "'
    2.32
    </caption>
    2.32
    Ce
    2.31
    Ke
    2.26
    router
    2.26
    pil
    2.26
    bur
    2.24
    """)
    2.23
    Activations Density 0.038%

    No Known Activations