© 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. 5337
    Prev
    Next
    INDEX
    Explanations

    try block

    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
     کد
    1.16
    вій
    1.16
    즌
    1.15
    çando
    1.14
    razi
    1.11
     xlab
    1.11
    ించాలని
    1.10
    وران
    1.09
     mohli
    1.09
     نوشت
    1.08
    POSITIVE LOGITS
    自有
    1.38
    ｪ
    1.35
    manner
    1.32
     manner
    1.29
    proton
    1.25
    setup
    1.25
    口气
    1.24
    made
    1.24
    ʼn
    1.24
    nance
    1.22
    Activations Density 0.151%

    No Known Activations