© 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. 119124
    Prev
    Next
    INDEX
    Explanations

    multidimensional array, threading, compose

    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
     antitumor
    -0.06
    Ltd
    -0.06
     assigning
    -0.06
    他的
    -0.06
    nnnn
    -0.06
     become
    -0.06
     применения
    -0.06
     jadi
    -0.06
    あるいは
    -0.06
     membahas
    -0.06
    POSITIVE LOGITS
    的位置
    0.06
     mõ
    0.06
    ar
    0.05
    말
    0.05
    希望
    0.05
     ఓ
    0.05
    garbage
    0.05
    違反
    0.05
     পরীক্ষ
    0.05
     pozy
    0.05
    Activations Density 0.162%

    No Known Activations