© 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. 117020
    Prev
    Next
    INDEX
    Explanations

    our cookies and privacy policy

    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
    Jet
    -0.06
     où
    -0.06
    盾
    -0.06
     nhé
    -0.06
     nosotros
    -0.06
    伌
    -0.06
    詞
    -0.06
     μας
    -0.06
     donde
    -0.06
     where
    -0.06
    POSITIVE LOGITS
     вчера
    0.07
     confidentiality
    0.07
    这两
    0.07
     *);
    0.07
     publicly
    0.06
     Confidential
    0.06
     प्रत्येक
    0.06
     стара
    0.06
    这两个
    0.06
    每个
    0.06
    Activations Density 0.001%

    No Known Activations