© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12732
    Prev
    Next
    INDEX
    Explanations

    game clone

    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
    phdr
    2.19
    <unused682>
    2.18
    <unused1855>
    2.14
    ⧐
    2.12
    <unused760>
    2.10
    <unused997>
    2.07
     使っ
    2.07
     指
    2.05
     Χ
    2.05
    <unused1670>
    2.04
    POSITIVE LOGITS
    s
    1.47
     Dadurch
    1.46
    رځ
    1.43
    なった
    1.40
    なら
    1.40
     както
    1.38
    ták
    1.33
    これで
    1.31
    र्थ
    1.31
     wodurch
    1.31
    Activations Density 0.061%

    No Known Activations