© 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. 120393
    Prev
    Next
    INDEX
    Explanations

    keep to maintain

    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
     morphed
    -0.06
     рекоменду
    -0.06
     recommend
    -0.06
    (*´
    -0.06
     characteristics
    -0.06
     atypical
    -0.06
     рассчиты
    -0.06
     per
    -0.06
    촬영
    -0.06
     managerial
    -0.06
    POSITIVE LOGITS
    Keeping
    0.07
     dostępne
    0.07
     lengthy
    0.06
    猖
    0.06
     reputable
    0.06
    ietta
    0.06
    addressed
    0.06
     Tentang
    0.06
    कृत
    0.06
     lifes
    0.06
    Activations Density 0.061%

    No Known Activations