© 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. 116873
    Prev
    Next
    INDEX
    Explanations

    release notes and changes

    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
    
    -0.06
     proved
    -0.06
     increases
    -0.06
    :
    -0.06
    efficacité
    -0.06
    inals
    -0.06
    elevation
    -0.06
     пяти
    -0.06
     пять
    -0.06
    یمی
    -0.05
    POSITIVE LOGITS
     Gourmet
    0.06
     fellowship
    0.06
     like
    0.06
     intangible
    0.05
     مثل
    0.05
    ଠ
    0.05
     Conv
    0.05
     cosa
    0.05
    нь
    0.05
     ভেতর
    0.05
    Activations Density 0.003%

    No Known Activations