© 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. 118402
    Prev
    Next
    INDEX
    Explanations

    countries followed by specific 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
    Not in Any Lists

    No Comments

    Negative Logits
     zusätzlichen
    -0.06
     додат
    -0.06
     വീ
    -0.06
     sofort
    -0.06
     추가
    -0.06
     одну
    -0.06
     zusätzliche
    -0.06
     Thailand
    -0.06
    provision
    -0.06
     smartphone
    -0.06
    POSITIVE LOGITS
     unjustly
    0.07
    Med
    0.06
    Good
    0.06
     bioc
    0.06
    omyc
    0.05
    entiary
    0.05
     сьогодні
    0.05
    :
    0.05
    等着
    0.05
     intersects
    0.05
    Activations Density 0.083%

    No Known Activations