© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115993
    Prev
    Next
    INDEX
    Explanations

    @ followed by programming keywords

    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
    Negative Logits
     necess
    -0.08
     necessary
    -0.07
     neces
    -0.06
     significative
    -0.06
     necessitate
    -0.06
     necessitating
    -0.06
     necessità
    -0.06
     beautiful
    -0.06
     necessitated
    -0.06
    الم
    -0.06
    POSITIVE LOGITS
     poplar
    0.07
     შედ
    0.06
     criteri
    0.06
    դ
    0.06
    телно
    0.06
    ljenje
    0.06
    હુ
    0.06
     могут
    0.06
     criteria
    0.06
     конден
    0.06
    Activations Density 0.002%

    No Known Activations