© 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. 120397
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
    whereas
    -0.06
     whereas
    -0.06
    হল
    -0.06
     mexicanos
    -0.06
    ƌ
    -0.06
     microstructure
    -0.06
    を用いて
    -0.06
    irectional
    -0.06
     considérable
    -0.06
    USSR
    -0.06
    POSITIVE LOGITS
    global
    0.07
     global
    0.06
     실패
    0.06
    初期
    0.06
     comme
    0.06
     
    0.06
    关于
    0.06
    ",
    0.06
     failed
    0.06
     শা
    0.06
    Activations Density 0.004%

    No Known Activations