© 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. 130783
    Prev
    Next
    INDEX
    Explanations

    book titles or phrases

    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
     पेड़
    -0.06
    ❣️
    -0.06
     certes
    -0.06
    在哪里
    -0.06
    ifen
    -0.06
     chefs
    -0.06
     zatím
    -0.06
    $(".
    -0.06
     nasıl
    -0.06
    毕竟
    -0.06
    POSITIVE LOGITS
     get
    0.06
     Get
    0.06
     στο
    0.06
     அடுத்த
    0.06
     in
    0.06
     sắp
    0.06
     ELSE
    0.06
     இன்னொரு
    0.06
    等
    0.06
     Ко
    0.06
    Activations Density 0.015%

    No Known Activations