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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130952
    Prev
    Next
    INDEX
    Explanations

    usually, usually, Usually, commonly

    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
    を実施
    -0.06
     baza
    -0.06
    教師
    -0.06
     топо
    -0.06
    ernen
    -0.06
     enseignants
    -0.06
     गरजे
    -0.06
     oke
    -0.06
    อยาก
    -0.06
    CONFIGURATION
    -0.06
    POSITIVE LOGITS
     usually
    0.08
    usually
    0.07
    通常
    0.07
    大多
    0.07
    Usually
    0.06
     वर्कर्स
    0.06
     чаще
    0.06
     satisfactor
    0.06
    Disclaimer
    0.06
     commonly
    0.06
    Activations Density 0.001%

    No Known Activations