© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120736
    Prev
    Next
    INDEX
    Explanations

    removal and disassembly

    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
     failure
    -0.06
    傆
    -0.06
     sprouting
    -0.06
     Lebens
    -0.06
     Slowly
    -0.06
     оста
    -0.06
     Ер
    -0.06
     remaining
    -0.06
     Remains
    -0.06
    ใส่
    -0.05
    POSITIVE LOGITS
     anche
    0.07
     temporarily
    0.06
     précédemment
    0.06
    在他
    0.06
    初心者
    0.06
    вать
    0.06
    としても
    0.06
     him
    0.06
    เขา
    0.06
     Empowerment
    0.06
    Activations Density 0.007%

    No Known Activations