© 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. 119667
    Prev
    Next
    INDEX
    Explanations

    review queues

    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
    内容的
    -0.08
     servizi
    -0.07
     what
    -0.07
    encour
    -0.06
     Fragen
    -0.06
    ኼ
    -0.06
    内容
    -0.06
     fonctionner
    -0.06
    What
    -0.06
     sincerity
    -0.06
    POSITIVE LOGITS
     nowadays
    0.07
     before
    0.06
     Nowadays
    0.06
    日常
    0.06
     martes
    0.06
     antes
    0.06
     பொதுவாக
    0.06
     modern
    0.06
    Nowadays
    0.06
     trước
    0.06
    Activations Density 0.016%

    No Known Activations