© 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. 129179
    Prev
    Next
    INDEX
    Explanations

    mobility degradation, electromigration, change, calcium influx, electron tunneling

    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
     तैयारियों
    -0.06
     eliminate
    -0.06
     Producto
    -0.06
     namun
    -0.06
     memberikan
    -0.06
     দিতে
    -0.06
     każdy
    -0.06
     imati
    -0.06
    दमी
    -0.06
     give
    -0.06
    POSITIVE LOGITS
    耧
    0.06
     prioritized
    0.06
     காப்பா
    0.06
    Up
    0.06
     такая
    0.06
    oped
    0.06
     aniversario
    0.06
     DPS
    0.06
     quelquefois
    0.06
     voc
    0.05
    Activations Density 0.001%

    No Known Activations