© 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. 119672
    Prev
    Next
    INDEX
    Explanations

    fall and trip

    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
    哔
    -0.06
     claimants
    -0.06
    लोक
    -0.06
    ijk
    -0.05
    щаем
    -0.05
     other
    -0.05
    Multipart
    -0.05
    Wikimedia
    -0.05
    irregular
    -0.05
    pture
    -0.05
    POSITIVE LOGITS
    😴
    0.07
     glum
    0.07
     thoughts
    0.07
    😔
    0.06
    analisi
    0.06
    🤒
    0.06
     dots
    0.06
     এসব
    0.06
    憔
    0.06
    💤
    0.06
    Activations Density 0.008%

    No Known Activations