© 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. 118400
    Prev
    Next
    INDEX
    Explanations

    only happens

    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
     heath
    -0.07
     health
    -0.07
     Health
    -0.06
     need
    -0.06
     Ото
    -0.06
    为什么要
    -0.06
     constraints
    -0.06
    akumar
    -0.06
    文字
    -0.06
     nutrient
    -0.06
    POSITIVE LOGITS
     வெவ்வேறு
    0.08
     разными
    0.08
     разных
    0.07
    different
    0.07
     früheren
    0.07
     verschied
    0.06
     diferentes
    0.06
     different
    0.06
    Tiny
    0.06
     связаны
    0.06
    Activations Density 0.025%

    No Known Activations