© 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. 10816
    Prev
    Next
    INDEX
    Explanations

    dashboard, panel, dispensing

    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
    <bos>
    2.47
    loose
    2.04
    West
    1.94
    way
    1.92
    west
    1.92
     Moving
    1.90
    কুট
    1.88
     Uno
    1.87
    rasp
    1.86
    ধরনের
    1.85
    POSITIVE LOGITS
    %%%%%%%%%%%%
    2.76
    ври
    2.51
    ្អ
    2.43
    FileChooser
    2.43
    ක
    2.43
    蔔
    2.41
    س
    2.36
    IRCONIUM
    2.34
     `=
    2.31
    пети
    2.30
    Activations Density 0.008%

    No Known Activations