© 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. 120837
    Prev
    Next
    INDEX
    Explanations

    and/or conjunctions

    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
     other
    -0.08
    以外の
    -0.08
    其它
    -0.08
     ఇతర
    -0.08
     другие
    -0.07
     نہیں
    -0.07
     selain
    -0.07
    但是
    -0.07
    Soon
    -0.07
    其他的
    -0.07
    POSITIVE LOGITS
     그러니까
    0.07
     ništa
    0.06
     ஒன்று
    0.06
    third
    0.06
    esthetic
    0.06
     destinados
    0.06
     broadest
    0.06
     kõige
    0.06
     fourth
    0.06
     والمع
    0.06
    Activations Density 0.039%

    No Known Activations