© 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. 129303
    Prev
    Next
    INDEX
    Explanations

    main result, objective, idea, contribution

    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
    5
    -0.07
     ближай
    -0.06
     phr
    -0.06
     которых
    -0.06
     disponibili
    -0.06
     આવ્યો
    -0.06
     небольшой
    -0.06
    らなかった
    -0.06
    anesi
    -0.06
     которой
    -0.06
    POSITIVE LOGITS
    არა
    0.06
     उतरे
    0.06
     않는
    0.06
    contrar
    0.06
    ill
    0.05
     Crohn
    0.05
     prone
    0.05
     git
    0.05
     ক্রম
    0.05
     representing
    0.05
    Activations Density 0.001%

    No Known Activations