© 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. 1654
    Prev
    Next
    INDEX
    Explanations

    exception handling in code

    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
    ͡
    1.42
     AppCompat
    1.40
     Vedi
    1.39
     crede
    1.33
    いを
    1.33
    Ħ
    1.32
    びに
    1.32
    documentclass
    1.32
    }--\
    1.31
    ReadLine
    1.31
    POSITIVE LOGITS
    uma
    0.87
    tru
    0.84
    fontein
    0.75
    Structural
    0.68
    Taxi
    0.65
    Children
    0.64
    ters
    0.64
    UMA
    0.63
    um
    0.60
    tant
    0.59
    Activations Density 0.293%

    No Known Activations