© 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. 115959
    Prev
    Next
    INDEX
    Explanations

    Drug addiction

    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
     possui
    -0.06
     വ്യ
    -0.06
     pemilik
    -0.06
     যেতে
    -0.06
     छुट्टी
    -0.06
     właścic
    -0.06
     konfigur
    -0.06
     keine
    -0.06
     enige
    -0.06
     bởi
    -0.06
    POSITIVE LOGITS
    ϳ
    0.07
    有效的
    0.06
     efficace
    0.06
    adress
    0.06
    previously
    0.06
    already
    0.06
     bogey
    0.06
    Previously
    0.06
     ঢাকার
    0.06
    Already
    0.06
    Activations Density 0.028%

    No Known Activations