© 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. 118667
    Prev
    Next
    INDEX
    Explanations

    contextual punctuation and 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
    Should
    -0.06
     செய்யலாம்
    -0.06
    imai
    -0.06
    (.*
    -0.06
     initially
    -0.06
     化
    -0.06
     Stove
    -0.06
     suic
    -0.05
     Related
    -0.05
     eerst
    -0.05
    POSITIVE LOGITS
     ভয়ঙ্কর
    0.06
    ຕົວ
    0.06
     кө
    0.06
     genau
    0.06
     হয়েছে
    0.06
     যথার্থ
    0.06
    после
    0.06
    明确
    0.06
    adorable
    0.06
     που
    0.06
    Activations Density 0.003%

    No Known Activations