© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 119097
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or comparisons

    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
     اہل
    -0.07
     insanların
    -0.07
     każdym
    -0.06
    人と
    -0.06
    উত্তর
    -0.06
     anthropogenic
    -0.06
    だけど
    -0.06
    คน
    -0.06
    निम्नलिखित
    -0.06
     weekends
    -0.06
    POSITIVE LOGITS
     as
    0.08
     уже
    0.07
     on
    0.07
    เป็น
    0.06
     по
    0.06
    が
    0.06
     вже
    0.06
     особенно
    0.06
     почти
    0.06
     практически
    0.06
    Activations Density 0.007%

    No Known Activations