© 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. 116265
    Prev
    Next
    INDEX
    Explanations

    Gov

    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
     ouvre
    -0.07
     नया
    -0.06
     لأنه
    -0.06
     necesario
    -0.06
     pā
    -0.06
     même
    -0.06
    因为
    -0.06
     hesit
    -0.06
     tense
    -0.06
    䄳
    -0.06
    POSITIVE LOGITS
     more
    0.08
     that
    0.07
     مذکور
    0.07
     you
    0.07
     пры
    0.06
     specific
    0.06
     "',
    0.06
     более
    0.06
     an
    0.06
     discharge
    0.06
    Activations Density 0.001%

    No Known Activations