© 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. 119974
    Prev
    Next
    INDEX
    Explanations

    key, crucial, or important followed by a concept

    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
     global
    -0.05
    他
    -0.05
    最も
    -0.05
     Schumann
    -0.05
    系
    -0.05
    までに
    -0.05
     sicherlich
    -0.05
     évident
    -0.05
     সম্ভব
    -0.05
     эффективность
    -0.05
    POSITIVE LOGITS
     having
    0.07
     Instead
    0.07
     not
    0.07
    哪里
    0.07
    Instead
    0.07
    associazione
    0.06
     such
    0.06
     स्टेडियम
    0.06
    Unlike
    0.06
    Because
    0.06
    Activations Density 0.008%

    No Known Activations