© 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. 128440
    Prev
    Next
    INDEX
    Explanations

    html table tags

    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
     relevant
    -0.06
     have
    -0.06
     mTOR
    -0.06
     microglia
    -0.06
     liegen
    -0.06
     harvesting
    -0.06
     provide
    -0.06
     relevante
    -0.06
     компетен
    -0.06
     stayed
    -0.06
    POSITIVE LOGITS
    leh
    0.07
     ፈ
    0.06
     सर्जरी
    0.06
     Forma
    0.06
     hình
    0.06
     idioma
    0.06
     전체
    0.05
     melhor
    0.05
     guests
    0.05
     সৈন্যরা
    0.05
    Activations Density 0.001%

    No Known Activations