© 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. 129765
    Prev
    Next
    INDEX
    Explanations

    hereinafter to be described

    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
     such
    -0.06
     selectable
    -0.06
     special
    -0.06
     Special
    -0.06
    evo
    -0.06
     auss
    -0.05
    特殊
    -0.05
     Important
    -0.05
    残留
    -0.05
    回调
    -0.05
    POSITIVE LOGITS
     сега
    0.08
    真的很
    0.07
     उनके
    0.07
     ahora
    0.06
     derzeit
    0.06
     njihov
    0.06
     진짜
    0.06
    真的是
    0.06
     লক্ষ্যে
    0.06
     leurs
    0.06
    Activations Density 0.001%

    No Known Activations