© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4339
    Prev
    Next
    INDEX
    Explanations

    model output, code, and names

    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
     snooze
    1.38
     faute
    1.27
     duvet
    1.23
    >]</
    1.22
    딪
    1.21
    acetamol
    1.21
     Nulla
    1.21
    闷
    1.21
     domic
    1.20
    悶
    1.19
    POSITIVE LOGITS
    Williams
    2.04
     Williams
    2.01
     williams
    1.47
     Amherst
    1.40
     Spielberg
    1.36
     Williamsburg
    1.32
     WILLIAMS
    1.28
    Buffalo
    1.22
    illiams
    1.22
     PBS
    1.22
    Activations Density 0.011%

    No Known Activations