© 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. 1663
    Prev
    Next
    INDEX
    Explanations

    China currency Chinese Yuan

    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
    ी
    2.79
    catcher
    2.75
     qīng
    2.66
     artificielle
    2.66
    преде
    2.58
    ি
    2.55
    ಿಯಾ
    2.53
     wèi
    2.53
    ggio
    2.53
    ூர
    2.53
    POSITIVE LOGITS
    rolled
    2.27
    বীন্দ্র
    2.22
    ahme
    2.13
    ্ড
    2.03
    exion
    2.00
    ews
    1.99
    omial
    1.99
     fe
    1.98
    었
    1.96
    者に
    1.93
    Activations Density 0.523%

    No Known Activations