© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3888
    Prev
    Next
    INDEX
    Explanations

    Python exception handling

    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
     benefici
    1.31
    利
    1.25
    prest
    1.24
    ('${
    1.21
    𝕣
    1.19
    öh
    1.14
    arino
    1.13
    帐
    1.12
    ريس
    1.11
    posal
    1.09
    POSITIVE LOGITS
     Kanji
    1.46
     Tutt
    1.44
    umap
    1.42
     Coats
    1.41
     chắn
    1.41
     recessive
    1.41
     Scattered
    1.41
     Arrivals
    1.41
    atcher
    1.41
     Sparrow
    1.40
    Activations Density 0.000%

    No Known Activations