© 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. 119644
    Prev
    Next
    INDEX
    Explanations

    Q: / Month:

    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
    っぱ
    -0.07
    ütter
    -0.07
    高兴
    -0.06
     celor
    -0.06
     enough
    -0.06
    presidente
    -0.06
     presidente
    -0.06
     analyzer
    -0.06
     व्यावसायिक
    -0.06
     reborn
    -0.06
    POSITIVE LOGITS
     While
    0.06
     নগর
    0.06
     হাট
    0.06
    seem
    0.06
     may
    0.05
     peuvent
    0.05
     могут
    0.05
    易
    0.05
     கூடு
    0.05
     pueden
    0.05
    Activations Density 0.017%

    No Known Activations