© 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. 129129
    Prev
    Next
    INDEX
    Explanations

    formed group names

    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
     City
    -0.07
     city
    -0.07
     civic
    -0.06
    のお
    -0.06
     House
    -0.06
     one
    -0.06
    要求
    -0.06
     جمہوری
    -0.06
     police
    -0.06
    公民
    -0.06
    POSITIVE LOGITS
     formed
    0.08
     integrated
    0.07
     اليمن
    0.07
     intégré
    0.07
     undetected
    0.06
     reportedly
    0.06
     subsidiary
    0.06
    trends
    0.06
    Integrated
    0.06
     entirely
    0.06
    Activations Density 0.018%

    No Known Activations