© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118397
    Prev
    Next
    INDEX
    Explanations

    power, actions, ki, validated, strategies

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ආරක්ෂ
    -0.08
     proteção
    -0.08
    া
    -0.07
     mengirim
    -0.07
     Sada
    -0.07
     protección
    -0.07
     ইতিমধ্যেই
    -0.06
     protection
    -0.06
     도착
    -0.06
     Gericht
    -0.06
    POSITIVE LOGITS
    Mental
    0.07
     Mental
    0.06
    操
    0.06
    🅾
    0.06
     mental
    0.06
    প্রশ
    0.06
     Mô
    0.06
     restful
    0.06
    ține
    0.06
    WL
    0.05
    Activations Density 0.001%

    No Known Activations