© 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. 129587
    Prev
    Next
    INDEX
    Explanations

    formal introductory or linking phrases

    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
     это
    -0.07
     을
    -0.06
     这是
    -0.06
     를
    -0.06
     допомогою
    -0.06
     untitled
    -0.06
     اكيد
    -0.06
    अच्छ
    -0.06
     入
    -0.06
     ở
    -0.06
    POSITIVE LOGITS
     मिरर
    0.06
     cursus
    0.06
     toutefois
    0.06
     ремонт
    0.06
    لوان
    0.06
     rhiz
    0.06
    यू
    0.06
    OWER
    0.06
    However
    0.06
     ………………………………..
    0.05
    Activations Density 0.002%

    No Known Activations