© 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. 120927
    Prev
    Next
    INDEX
    Explanations

    over, out, extension

    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
    বিভিন্ন
    -0.07
     excepc
    -0.07
    芷
    -0.07
     વિવિધ
    -0.07
     വിവിധ
    -0.06
     பயன்படுத்த
    -0.06
     exorbitant
    -0.06
     pasó
    -0.06
    बहुत
    -0.06
     passato
    -0.06
    POSITIVE LOGITS
    以
    0.06
    мана
    0.05
    added
    0.05
    •
    0.05
     Tariff
    0.05
     menambah
    0.05
     כדי
    0.05
    data
    0.05
     attraction
    0.05
     zvyš
    0.05
    Activations Density 0.003%

    No Known Activations