© 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. 120261
    Prev
    Next
    INDEX
    Explanations

    remote server

    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
    NGO
    -0.06
    Consumer
    -0.06
     fokus
    -0.06
     consumer
    -0.06
     satu
    -0.06
     seminary
    -0.06
    महाराष्ट्र
    -0.06
     huv
    -0.06
     एवं
    -0.06
     use
    -0.06
    POSITIVE LOGITS
    illar
    0.06
     acquaintances
    0.06
     도착
    0.06
     equivalents
    0.06
     arkadaş
    0.06
    வரது
    0.06
    旅行
    0.06
     친구
    0.06
     مقصد
    0.06
     владель
    0.06
    Activations Density 0.008%

    No Known Activations