© 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. 119056
    Prev
    Next
    INDEX
    Explanations

    to Achieving or of Provision

    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
     cultural
    -0.07
     문화
    -0.06
     सांस्कृतिक
    -0.06
     culturale
    -0.05
     kulturn
    -0.05
     সাংস্কৃতিক
    -0.05
     Cultural
    -0.05
     interactive
    -0.05
    colorControl
    -0.05
     культур
    -0.05
    POSITIVE LOGITS
     respectivas
    0.06
     devast
    0.06
     vows
    0.06
     yells
    0.06
     majeure
    0.06
    બ્
    0.06
     jeweiligen
    0.06
    annten
    0.06
    大幅
    0.06
     швид
    0.06
    Activations Density 0.010%

    No Known Activations