© 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. 8134
    Prev
    Next
    INDEX
    Explanations

    buying and selling assets

    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
    으로써
    1.31
    }($
    1.30
     onRouteChange
    1.27
     (#{
    1.24
    ዦ
    1.21
    으로서
    1.21
    เช่น
    1.20
     으로
    1.19
    कडे
    1.19
    쏴
    1.17
    POSITIVE LOGITS
     tres
    1.12
     not
    1.06
     তিন
    1.02
    ­
    1.02
    not
    0.99
     joy
    0.97
     Hearts
    0.97
     duas
    0.97
     três
    0.97
     Par
    0.95
    Activations Density 0.002%

    No Known Activations