© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128383
    Prev
    Next
    INDEX
    Explanations

    NullPointerException and other exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     превы
    -0.07
     विपरीत
    -0.06
    これから
    -0.06
     Advers
    -0.06
    வரி
    -0.06
    єш
    -0.06
    advers
    -0.06
    と同じ
    -0.06
    LIST
    -0.06
     highways
    -0.06
    POSITIVE LOGITS
     很
    0.06
     REALLY
    0.06
     really
    0.06
     had
    0.06
     প্রকাশের
    0.06
     Messrs
    0.06
     ông
    0.06
     evidently
    0.06
    ?
    0.06
     bilgi
    0.05
    Activations Density 0.006%

    No Known Activations