© 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. 117338
    Prev
    Next
    INDEX
    Explanations

    economic development and quality of life

    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
     पर्वत
    -0.06
     identifik
    -0.06
     inicial
    -0.06
    識別
    -0.06
     regions
    -0.06
    ↵↵↵↵
    -0.06
    wr
    -0.05
    ↵↵↵↵↵↵
    -0.05
     各
    -0.05
     ancient
    -0.05
    POSITIVE LOGITS
     increase
    0.08
    增加
    0.07
     increases
    0.07
    我們
    0.07
     mainstay
    0.07
     aumento
    0.06
    lesen
    0.06
     lessening
    0.06
    PUT
    0.06
    我们
    0.06
    Activations Density 0.021%

    No Known Activations