© 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. 119456
    Prev
    Next
    INDEX
    Explanations

    dystrophin exon skipping

    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
    personas
    -0.06
    avance
    -0.06
     beads
    -0.06
     personas
    -0.06
    owels
    -0.06
    推动
    -0.06
    characters
    -0.06
    Difference
    -0.06
    romad
    -0.06
     பதவி
    -0.06
    POSITIVE LOGITS
     milliards
    0.07
     snowboard
    0.07
     magnetometer
    0.06
     المنتخب
    0.06
     adaptability
    0.06
     millions
    0.06
     linking
    0.06
     zagro
    0.06
     வாழ்க்கை
    0.06
     حدث
    0.06
    Activations Density 0.002%

    No Known Activations