© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118232
    Prev
    Next
    INDEX
    Explanations

    group by clause

    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
     combines
    -0.06
     blending
    -0.06
     blended
    -0.06
     habían
    -0.06
     леген
    -0.06
     immunization
    -0.05
     innerhalb
    -0.05
    updating
    -0.05
    वाया
    -0.05
    ellan
    -0.05
    POSITIVE LOGITS
     требования
    0.06
     требований
    0.06
     inadequate
    0.06
     Besar
    0.06
    jści
    0.06
    abt
    0.06
     //{
    0.06
     metropolis
    0.06
     seriously
    0.06
     TODO
    0.06
    Activations Density 0.003%

    No Known Activations