© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120412
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    hôte
    -0.06
     experimentos
    -0.06
    𝗹
    -0.06
     asiento
    -0.06
     ampere
    -0.06
     Cómo
    -0.06
    丅
    -0.06
     puta
    -0.06
    確実に
    -0.06
     sofern
    -0.06
    POSITIVE LOGITS
     необ
    0.06
     город
    0.06
     downtown
    0.06
     větš
    0.06
     অঞ্চলের
    0.06
     charisma
    0.05
     beantwort
    0.05
    完成
    0.05
    规划
    0.05
     ဖြစ်
    0.05
    Activations Density 0.000%

    No Known Activations