© 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. 116735
    Prev
    Next
    INDEX
    Explanations

    bible verses

    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
     even
    -0.07
    ⛔
    -0.06
     fundamental
    -0.06
     EVEN
    -0.06
    <blockquote>
    -0.06
     nawet
    -0.06
    लेले
    -0.06
     bijvoorbeeld
    -0.06
     концеп
    -0.06
    लेली
    -0.06
    POSITIVE LOGITS
     городе
    0.06
     recuer
    0.06
    注明
    0.06
    说道
    0.06
     বিষয়টি
    0.06
     произо
    0.06
     hâ
    0.06
     by
    0.06
    மை
    0.06
     аксе
    0.05
    Activations Density 0.003%

    No Known Activations