© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15549
    Prev
    Next
    INDEX
    Explanations

    specific formatting, code or structure

    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_13_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
    <unused677>
    1.77
    <unused586>
    1.75
    <unused1040>
    1.74
    <unused1531>
    1.69
     Kxh
    1.68
    <unused1522>
    1.68
    <unused1678>
    1.67
    <unused1831>
    1.66
    <unused1316>
    1.66
    <unused1162>
    1.66
    POSITIVE LOGITS
     plants
    1.08
     H
    1.05
    H
    1.01
    land
    0.96
     newly
    0.94
     new
    0.93
    Wrap
    0.92
     colors
    0.90
     stock
    0.89
     caps
    0.89
    Activations Density 0.000%

    No Known Activations