© 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. 120684
    Prev
    Next
    INDEX
    Explanations

    numbers and date-like sequences

    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
    เยี่ยม
    -0.06
     চক্ষু
    -0.06
     reclaim
    -0.06
     aquesta
    -0.06
     proposals
    -0.06
    భవ
    -0.06
     situation
    -0.06
    âu
    -0.06
     situations
    -0.06
    シップ
    -0.06
    POSITIVE LOGITS
     ——
    0.06
     خرید
    0.06
    ——
    0.06
     নিয়ন্ত্র
    0.05
    も
    0.05
    нных
    0.05
     ----
    0.05
    ———
    0.05
     masked
    0.05
     permeated
    0.05
    Activations Density 0.004%

    No Known Activations