© 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. 128740
    Prev
    Next
    INDEX
    Explanations

    business performance metrics

    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
     nationally
    -0.07
     ابتدائي
    -0.06
     precedence
    -0.06
    пуляр
    -0.06
    Mét
    -0.06
     purchaser
    -0.06
     favourably
    -0.06
     następnie
    -0.06
     popularly
    -0.06
     communicates
    -0.06
    POSITIVE LOGITS
     sebagaimana
    0.07
    每
    0.06
     merasa
    0.06
     dokon
    0.06
     chaque
    0.06
     ২০১৬
    0.06
    其中的
    0.06
    queeze
    0.06
    からも
    0.05
    单位
    0.05
    Activations Density 0.012%

    No Known Activations