© 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. 120823
    Prev
    Next
    INDEX
    Explanations

    Specific `Ig`, `Month`, `NAMES`

    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
     more
    -0.06
    (-
    -0.06
    之后
    -0.06
    /-
    -0.06
     cioè
    -0.06
    /
    -0.06
     পোশাক
    -0.05
     dobry
    -0.05
    之後
    -0.05
     Shift
    -0.05
    POSITIVE LOGITS
    ၎
    0.07
     这
    0.06
     जब
    0.06
     jika
    0.06
     색
    0.06
     portrays
    0.06
     hỗn
    0.06
     ඉතා
    0.06
     δο
    0.06
     сочета
    0.06
    Activations Density 0.001%

    No Known Activations