© 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. 130976
    Prev
    Next
    INDEX
    Explanations

    relative pronouns or conjunctions

    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
    <u>
    -0.07
    your
    -0.06
     while
    -0.06
     if
    -0.06
     Unite
    -0.06
     with
    -0.05
     YOUR
    -0.05
     like
    -0.05
    ness
    -0.05
    如
    -0.05
    POSITIVE LOGITS
     která
    0.07
     ktorá
    0.07
     которую
    0.07
    ''(
    0.07
     lla
    0.06
     পারিত
    0.06
     която
    0.06
     которая
    0.06
     beobachten
    0.06
     która
    0.06
    Activations Density 0.039%

    No Known Activations