© 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. 117657
    Prev
    Next
    INDEX
    Explanations

    baby sounds or words

    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
     آد
    -0.06
     Classified
    -0.06
     hend
    -0.06
     Meditation
    -0.06
     in
    -0.06
    issances
    -0.06
     страни
    -0.06
     Moto
    -0.06
    ანა
    -0.06
     Winkel
    -0.06
    POSITIVE LOGITS
    FAO
    0.06
     força
    0.06
     mật
    0.06
     به‌عنوان
    0.06
     req
    0.06
     plethora
    0.06
     rápida
    0.06
     الفلسطيني
    0.06
     fuerza
    0.06
     kids
    0.06
    Activations Density 0.045%

    No Known Activations