© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1554
    Prev
    Next
    INDEX
    Explanations

    representing the number nine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    <unused71>
    0.73
    ১৮
    0.68
    বৃহস্পতিবার
    0.66
    ২৮
    0.66
     Eighteenth
    0.63
     XVIII
    0.63
    <unused7>
    0.63
     Julie
    0.62
    ᱕
    0.61
    <unused52>
    0.60
    POSITIVE LOGITS
    ９
    3.54
    9
    3.42
    九
    3.26
     Nine
    3.19
    ۹
    3.12
     nine
    3.10
     ۹
    3.09
     ninety
    3.07
     девя
    3.03
    Nine
    2.97
    Activations Density 0.980%

    No Known Activations