© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1299
    Prev
    Next
    INDEX
    Explanations

    rate in the

    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
    ૢ
    1.75
    늠
    1.64
     తప్ప
    1.56
    newInstance
    1.56
    ancien
    1.53
    ࣪
    1.52
    ✺
    1.51
     최소
    1.49
    tey
    1.47
    ✥
    1.46
    POSITIVE LOGITS
     in
    6.06
     dalam
    4.63
    ใน
    4.02
     في
    4.01
     trong
    3.94
     In
    3.90
     в
    3.85
    in
    3.81
     فى
    3.80
    在
    3.76
    Activations Density 10.189%

    No Known Activations