© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131032
    Prev
    Next
    INDEX
    Explanations

    boolean comparison and conditional logic

    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
     którą
    -0.06
    แรก
    -0.06
     pierwszym
    -0.06
     первым
    -0.06
     первом
    -0.06
     vyst
    -0.06
     MINI
    -0.05
    初回
    -0.05
    充满了
    -0.05
    初の
    -0.05
    POSITIVE LOGITS
    boolean
    0.07
     boolean
    0.07
    ENVIRONMENT
    0.07
    이지만
    0.06
     statement
    0.06
     véritables
    0.06
     profundidad
    0.06
     Bool
    0.06
     stating
    0.06
     cliques
    0.06
    Activations Density 0.015%

    No Known Activations