© 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. 120129
    Prev
    Next
    INDEX
    Explanations

    Saint-Germain

    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
     chosen
    -0.06
    प्रतिनि
    -0.06
     を
    -0.06
     YOUR
    -0.06
     sinnv
    -0.06
     ultimate
    -0.06
     runes
    -0.06
     testament
    -0.06
    umuza
    -0.06
    Comp
    -0.06
    POSITIVE LOGITS
    它是
    0.06
     bijna
    0.06
     পৌর
    0.06
     електро
    0.06
    rake
    0.06
    पश्च
    0.06
    Видео
    0.06
    noof
    0.06
     there
    0.06
    就可以了
    0.06
    Activations Density 0.001%

    No Known Activations