© 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. 118916
    Prev
    Next
    INDEX
    Explanations

    court citations and regions

    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
     □
    -0.06
     attempted
    -0.06
     dislikes
    -0.06
    言
    -0.06
     policing
    -0.06
     hostilities
    -0.05
    வைகள்
    -0.05
     forcibly
    -0.05
     демокра
    -0.05
     upright
    -0.05
    POSITIVE LOGITS
     BOTH
    0.06
     훨씬
    0.06
     bigger
    0.06
     both
    0.06
    verbrauch
    0.06
    Workbook
    0.06
     både
    0.06
     bardziej
    0.06
    Both
    0.06
    就像
    0.06
    Activations Density 0.013%

    No Known Activations