© 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. 128732
    Prev
    Next
    INDEX
    Explanations

    save their partner

    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
     years
    -0.07
    颁
    -0.06
     issued
    -0.06
     ඔහු
    -0.06
    years
    -0.06
     किल्ला
    -0.06
    months
    -0.06
    Years
    -0.06
     months
    -0.06
    issu
    -0.06
    POSITIVE LOGITS
     tablespoons
    0.07
    পুরের
    0.07
    恶意
    0.06
    urias
    0.06
     SUVs
    0.06
     pareil
    0.06
     arterioles
    0.06
     إلى
    0.06
     온라인
    0.06
    ilus
    0.06
    Activations Density 0.001%

    No Known Activations