© 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. 15722
    Prev
    Next
    INDEX
    Explanations

    one versus another

    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
     citations
    2.22
     bookmarks
    2.19
    estamps
    2.07
    𝚒
    2.06
     placements
    2.04
    llllll
    2.03
     headers
    2.03
     sockets
    2.02
    𝚞
    2.02
    llllllll
    2.01
    POSITIVE LOGITS
    ০
    3.13
    加坡
    2.97
    ಿ
    2.61
    jų
    2.54
    ي
    2.51
    า
    2.48
    ი
    2.47
    sman
    2.46
    quela
    2.45
    ه
    2.43
    Activations Density 0.048%

    No Known Activations