© 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. 130433
    Prev
    Next
    INDEX
    Explanations

    sports officiating and judgment

    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
    ospitals
    -0.06
     cử
    -0.06
    special
    -0.06
    Tony
    -0.06
     ceremonial
    -0.05
    責任
    -0.05
     আটক
    -0.05
     gewüns
    -0.05
    ണ്ടാ
    -0.05
     специа
    -0.05
    POSITIVE LOGITS
     उद्यम
    0.07
    疑惑
    0.06
    acom
    0.06
     निष्क्रिय
    0.06
     मूल्यांकन
    0.06
     glTranslatef
    0.06
     patronage
    0.06
     historial
    0.06
     zbog
    0.05
     increasingly
    0.05
    Activations Density 0.001%

    No Known Activations