© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129770
    Prev
    Next
    INDEX
    Explanations

    App

    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
    even
    -0.06
    实质
    -0.06
    গুলোকে
    -0.06
    可以是
    -0.06
     அவை
    -0.06
    etition
    -0.06
     стал
    -0.06
    啻
    -0.05
     даже
    -0.05
     Buf
    -0.05
    POSITIVE LOGITS
     what
    0.07
     ご
    0.07
     constantly
    0.07
     然後
    0.07
     continually
    0.07
     What
    0.07
     Algunos
    0.07
     Acest
    0.07
     both
    0.06
     如果
    0.06
    Activations Density 0.008%

    No Known Activations