© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5549
    Prev
    Next
    INDEX
    Explanations

    human control or equity swap

    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
    래
    1.43
     مرات
    1.35
     除了
    1.20
     اتح
    1.19
     viss
    1.19
    igle
    1.19
     drills
    1.18
    ную
    1.17
     vertical
    1.17
    ្រ
    1.17
    POSITIVE LOGITS
    WebV
    1.45
    ки
    1.44
    [["
    1.44
    Files
    1.35
    frozen
    1.34
    CTR
    1.34
    ":[{"
    1.34
    FieldError
    1.33
    קור
    1.33
    thai
    1.33
    Activations Density 0.000%

    No Known Activations