© 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. 129741
    Prev
    Next
    INDEX
    Explanations

    discussion or examination of concepts

    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
     another
    -0.09
     autre
    -0.09
     또
    -0.08
     اخرى
    -0.08
     otra
    -0.08
     другого
    -0.08
     altro
    -0.07
     другое
    -0.07
    autre
    -0.07
     başka
    -0.07
    POSITIVE LOGITS
    များနှင့်
    0.07
     pictures
    0.06
     influencing
    0.06
     Items
    0.06
    udara
    0.06
     एग्जामिनेशन
    0.06
     quadrilateral
    0.06
    Kansas
    0.06
    来到了
    0.06
     automobil
    0.06
    Activations Density 0.040%

    No Known Activations