© 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. 120247
    Prev
    Next
    INDEX
    Explanations

    monster hunter, free, hyper, changes

    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
     ты
    -0.08
     قه
    -0.07
    ុល
    -0.06
    champion
    -0.06
    关于
    -0.06
     उनका
    -0.06
     plana
    -0.06
     socialist
    -0.06
    Cherry
    -0.06
    部分的
    -0.06
    POSITIVE LOGITS
     perceive
    0.06
     احتاج
    0.06
     Profession
    0.06
     Compress
    0.06
     едва
    0.06
     체험
    0.06
    तूल
    0.06
     ambos
    0.05
     উত্প
    0.05
    ほぼ
    0.05
    Activations Density 0.003%

    No Known Activations