© 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. 118078
    Prev
    Next
    INDEX
    Explanations

    numbers followed by dashes or other numbers

    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
     ensures
    -0.06
    และ
    -0.06
     ensure
    -0.06
     kiddos
    -0.06
     និង
    -0.06
     ilość
    -0.06
     주어진
    -0.06
    絶対に
    -0.05
     ಸಮಯದಲ್ಲಿ
    -0.05
     ensured
    -0.05
    POSITIVE LOGITS
     ahora
    0.07
     now
    0.07
     artık
    0.07
     теперь
    0.07
     కోసం
    0.06
     для
    0.06
     ذہن
    0.06
     विशेषताओं
    0.06
     이제
    0.06
     people
    0.06
    Activations Density 0.002%

    No Known Activations