© 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. 128128
    Prev
    Next
    INDEX
    Explanations

    rotor and roller components

    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
     slightly
    -0.07
    different
    -0.06
    บ้าง
    -0.06
     to
    -0.06
     DIFFERENT
    -0.06
     different
    -0.05
    Market
    -0.05
     differently
    -0.05
    少し
    -0.05
    不同的
    -0.05
    POSITIVE LOGITS
     územ
    0.07
    Diameter
    0.07
     आंतरिक
    0.06
    verification
    0.06
    Verification
    0.06
     INTERACTIONS
    0.06
     измере
    0.06
    ონის
    0.06
     الداخل
    0.06
     সবুজ
    0.06
    Activations Density 0.023%

    No Known Activations