© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118950
    Prev
    Next
    INDEX
    Explanations

    objects described with possessives or unique names

    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
     necessary
    -0.08
     જરૂરી
    -0.07
    必要な
    -0.07
     gerekiyor
    -0.07
     required
    -0.06
     necessario
    -0.06
    血液
    -0.06
     necessaria
    -0.06
    required
    -0.06
     nécessaire
    -0.06
    POSITIVE LOGITS
     yıll
    0.07
     authentically
    0.07
     verdadera
    0.07
     अड्डा
    0.06
     réellement
    0.06
     nonché
    0.06
     autént
    0.06
     discrepancies
    0.06
    生意
    0.06
    authent
    0.06
    Activations Density 0.023%

    No Known Activations