© 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. 128015
    Prev
    Next
    INDEX
    Explanations

    media coverage ignored

    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
     conceivable
    -0.06
     amenaza
    -0.06
    ஞ்ஞான
    -0.06
    माजिक
    -0.06
     rumors
    -0.06
    quine
    -0.06
     möglich
    -0.06
    UNKNOWN
    -0.06
    可能性がある
    -0.06
     rumored
    -0.06
    POSITIVE LOGITS
    視聴
    0.06
    反复
    0.06
     apoy
    0.05
    爱情
    0.05
     فراہم
    0.05
     Funktions
    0.05
     rectified
    0.05
     clarity
    0.05
     رح
    0.05
     göstere
    0.05
    Activations Density 0.011%

    No Known Activations