© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130475
    Prev
    Next
    INDEX
    Explanations

    night

    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
     vous
    -0.06
    ıyorum
    -0.06
     माझ्या
    -0.06
     как
    -0.06
     भोले
    -0.06
    と一緒に
    -0.06
    डीएम
    -0.06
    मिली
    -0.06
     tengo
    -0.06
     तुमच्या
    -0.05
    POSITIVE LOGITS
     голе
    0.06
    몫
    0.06
    ozat
    0.06
     এট
    0.06
    દર્
    0.06
     vitally
    0.06
    អាច
    0.06
     difficile
    0.06
     timet
    0.05
     profundamente
    0.05
    Activations Density 0.003%

    No Known Activations