© 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. 120401
    Prev
    Next
    INDEX
    Explanations

    Shopping Cart, Photo Shows, Chordee

    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
     эсеп
    -0.06
     Classroom
    -0.06
     eğitimi
    -0.06
     आवृत्ति
    -0.06
     consegn
    -0.06
     émissions
    -0.06
     towns
    -0.06
     Appalach
    -0.06
     матери
    -0.06
     культур
    -0.06
    POSITIVE LOGITS
     Photoshop
    0.07
    Disabled
    0.07
    िस
    0.07
     Tarot
    0.06
    美女
    0.06
     badly
    0.06
    று
    0.06
     этого
    0.06
     precluded
    0.06
     relying
    0.06
    Activations Density 0.009%

    No Known Activations