© 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. 117916
    Prev
    Next
    INDEX
    Explanations

    legal and technical jargon

    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
     Enjoy
    -0.06
    Enjoy
    -0.06
     Robert
    -0.06
     zweite
    -0.06
     David
    -0.06
     hydrant
    -0.06
     enjoy
    -0.06
    subject
    -0.06
    ::~
    -0.06
     Answer
    -0.06
    POSITIVE LOGITS
     jika
    0.07
     Burkina
    0.06
     নথি
    0.06
    수가
    0.06
     nếu
    0.06
    сси
    0.05
     Nutritional
    0.05
     jų
    0.05
     मालिकों
    0.05
    issime
    0.05
    Activations Density 0.016%

    No Known Activations