© 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. 116521
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or comparison words

    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
    PlayerData
    -0.07
     ongeveer
    -0.07
     approximately
    -0.07
     Krzysz
    -0.07
     exhilar
    -0.06
     [[
    -0.06
     ██
    -0.06
    🐒
    -0.06
    그런
    -0.06
     complementar
    -0.06
    POSITIVE LOGITS
     ইন্ডাস্ট্র
    0.06
     website
    0.06
    进而
    0.06
     دیر
    0.06
    还可以
    0.06
     countless
    0.06
    website
    0.06
    并
    0.05
     ا
    0.05
     不
    0.05
    Activations Density 0.005%

    No Known Activations