© 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. 1244
    Prev
    Next
    INDEX
    Explanations

    error handling and exceptions

    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
     مفه
    1.48
    šek
    1.43
    mixing
    1.41
     Flinders
    1.39
    graphicx
    1.37
     Macedonian
    1.36
    rivere
    1.34
    쏨
    1.32
    austral
    1.31
    RIGHT
    1.31
    POSITIVE LOGITS
     sickness
    1.27
     tradition
    1.18
     diagnosis
    1.10
     tenure
    1.09
     mode
    1.08
     h
    1.08
     tenacity
    1.07
     desider
    1.06
     respons
    1.06
     il
    1.06
    Activations Density 0.002%

    No Known Activations