© 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. 115939
    Prev
    Next
    INDEX
    Explanations

    without compromising

    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
    !!!!!
    -0.06
    ঠু
    -0.06
    !!!!
    -0.06
    沒有
    -0.06
    ?????
    -0.06
    关系
    -0.06
     !!!!!
    -0.06
     não
    -0.06
    Prefer
    -0.05
    !!!!!!
    -0.05
    POSITIVE LOGITS
     refocus
    0.06
     служит
    0.06
     explored
    0.06
     strengthen
    0.06
     enhances
    0.06
     commended
    0.06
     urs
    0.06
     descub
    0.06
     Exploring
    0.06
     explores
    0.06
    Activations Density 0.018%

    No Known Activations