© 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. 116351
    Prev
    Next
    INDEX
    Explanations

    legal case party titles

    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
     плюс
    -0.06
     взаимодей
    -0.06
     neighbouring
    -0.06
    टिया
    -0.06
    本の
    -0.05
    ьо
    -0.05
     от
    -0.05
     Danube
    -0.05
    eflow
    -0.05
     शीघ्र
    -0.05
    POSITIVE LOGITS
     Updating
    0.06
     Thus
    0.06
    更新
    0.06
    updating
    0.06
     更新
    0.06
     Remember
    0.06
     तयारी
    0.06
     crumbled
    0.06
     Know
    0.05
     फैन
    0.05
    Activations Density 0.003%

    No Known Activations