© 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. 128672
    Prev
    Next
    INDEX
    Explanations

    Hubble Space, DNA fragmentation, Riverdale, Alan Mackin

    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
     typical
    -0.06
     Typical
    -0.06
     típico
    -0.06
    Typical
    -0.06
    リスト
    -0.06
     elected
    -0.06
    Selected
    -0.06
    經典
    -0.06
    號
    -0.06
     এলাকার
    -0.06
    POSITIVE LOGITS
     feder
    0.07
    feder
    0.07
     synchronization
    0.07
     longitudinal
    0.06
    各国
    0.06
     Perman
    0.06
     admittance
    0.06
     assorted
    0.06
     permanently
    0.06
     planks
    0.06
    Activations Density 0.002%

    No Known Activations