© 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. 128143
    Prev
    Next
    INDEX
    Explanations

    negotiator, types, zero

    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
     khá
    -0.07
     assez
    -0.07
     pensée
    -0.07
     dość
    -0.06
     досить
    -0.06
     nutzen
    -0.06
     ন্যায়
    -0.06
     एंज
    -0.06
     conscient
    -0.06
     abbastanza
    -0.06
    POSITIVE LOGITS
     Clamp
    0.06
    getType
    0.06
     ID
    0.06
     типов
    0.06
     tipos
    0.06
     அவற்ற
    0.06
    特定
    0.06
    TV
    0.06
    Types
    0.06
     types
    0.06
    Activations Density 0.005%

    No Known Activations