© 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. 119367
    Prev
    Next
    INDEX
    Explanations

    numbers, names, and specific words

    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
     cuando
    -0.07
    Oui
    -0.06
     उन्नति
    -0.06
     iu
    -0.06
    Explained
    -0.06
     ఇప్పటికే
    -0.06
     WHEN
    -0.06
     celý
    -0.06
    理由は
    -0.06
    已
    -0.06
    POSITIVE LOGITS
     Jahrhund
    0.06
    Brown
    0.06
    ிருந்த
    0.06
    Direct
    0.06
    ிகா
    0.06
     सावधानी
    0.05
     Becker
    0.05
    accouchement
    0.05
     subconsciously
    0.05
     help
    0.05
    Activations Density 0.019%

    No Known Activations