© 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. 128948
    Prev
    Next
    INDEX
    Explanations

    proper nouns and news headings

    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
    gente
    -0.06
    btw
    -0.06
     prévu
    -0.06
     Strictly
    -0.06
    他們的
    -0.06
     leurs
    -0.06
     alarming
    -0.06
     실제로
    -0.06
     schoolchildren
    -0.06
     Soccer
    -0.06
    POSITIVE LOGITS
     যোগ্যতা
    0.06
     novità
    0.06
    ４
    0.06
    具备
    0.06
     năm
    0.06
     ඉක්
    0.06
    INGO
    0.05
    3
    0.05
     easily
    0.05
     quickly
    0.05
    Activations Density 0.001%

    No Known Activations