© 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. 129743
    Prev
    Next
    INDEX
    Explanations

    lengths, chain

    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
     operates
    -0.06
     பகுதியை
    -0.06
     demais
    -0.06
     ইউরোপ
    -0.06
     остальные
    -0.06
     assuming
    -0.06
     करणारे
    -0.06
     என்க
    -0.06
     becomes
    -0.06
    ルー
    -0.06
    POSITIVE LOGITS
    best
    0.06
     clang
    0.06
     這
    0.06
     effective
    0.06
     Diesel
    0.06
     Several
    0.05
     সন্ত্রাসী
    0.05
    extern
    0.05
    Austral
    0.05
    numer
    0.05
    Activations Density 0.001%

    No Known Activations