© 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. 116662
    Prev
    Next
    INDEX
    Explanations

    ensure that

    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
     كثيرا
    -0.07
     genellikle
    -0.06
     Cutter
    -0.06
     other
    -0.06
     greatly
    -0.06
     expliqué
    -0.06
     then
    -0.06
     but
    -0.06
    leriyle
    -0.06
    ButtonClick
    -0.06
    POSITIVE LOGITS
    proper
    0.07
     потенциа
    0.06
    同じ
    0.06
     replicas
    0.06
     oportunidades
    0.06
     kịp
    0.06
    適切な
    0.06
    formal
    0.06
     Slovakia
    0.06
    opportunities
    0.05
    Activations Density 0.023%

    No Known Activations