© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128008
    Prev
    Next
    INDEX
    Explanations

    software licensing and code comments

    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
    Negative Logits
     Обычно
    -0.07
    直接
    -0.06
    ITHUB
    -0.06
    窃
    -0.06
    usually
    -0.06
     hitbox
    -0.06
     bezpośred
    -0.06
    Usually
    -0.06
     Usually
    -0.06
     usually
    -0.06
    POSITIVE LOGITS
     την
    0.06
    ជាមួយ
    0.06
     Scandinavian
    0.06
     οι
    0.06
     क्रमश
    0.06
     været
    0.06
     עם
    0.06
    سل
    0.06
     друзья
    0.06
     तौर
    0.06
    Activations Density 0.002%

    No Known Activations