© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6575
    Prev
    Next
    INDEX
    Explanations

    easier, maintainable, understandable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     denominated
    1.11
     esforços
    1.08
    OptionsMenu
    1.07
     assayed
    1.06
    forceable
    1.03
     levied
    1.03
     stren
    1.03
    勲
    1.02
    電圧
    1.00
    纽
    1.00
    POSITIVE LOGITS
     นึง
    1.68
    yh
    1.59
    uyễn
    1.53
    partisan
    1.52
    itys
    1.47
    ẳng
    1.43
     สัก
    1.41
    uyu
    1.40
    ibernate
    1.40
    ｙ
    1.37
    Activations Density 0.019%

    No Known Activations