© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118329
    Prev
    Next
    INDEX
    Explanations

    schools or difficult study

    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
     must
    -0.06
    不得
    -0.06
    wreck
    -0.06
    लांग
    -0.06
     probably
    -0.06
     rod
    -0.05
    access
    -0.05
     تازه
    -0.05
     lip
    -0.05
    ak
    -0.05
    POSITIVE LOGITS
    它
    0.07
     школе
    0.07
     rigorous
    0.07
     它
    0.07
     escuelas
    0.07
     artisanal
    0.07
     grueling
    0.06
     Schulen
    0.06
     одну
    0.06
     tedious
    0.06
    Activations Density 0.013%

    No Known Activations