© 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. 127908
    Prev
    Next
    INDEX
    Explanations

    company news","access to online","freedom of expression"

    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
     locatie
    -0.07
     notary
    -0.07
    比特币
    -0.06
     of
    -0.06
    繹
    -0.06
     finalizar
    -0.06
     συνε
    -0.06
     adjour
    -0.06
    可以用
    -0.06
     loopholes
    -0.06
    POSITIVE LOGITS
     sold
    0.06
     نیچے
    0.06
     жан
    0.06
     Transport
    0.06
     nutrition
    0.06
    features
    0.06
     напря
    0.06
    总经理
    0.05
     features
    0.05
     на
    0.05
    Activations Density 0.004%

    No Known Activations