© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119464
    Prev
    Next
    INDEX
    Explanations

    required, Police, How, I

    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
     many
    -0.08
     always
    -0.07
     trendy
    -0.06
     بسیاری
    -0.06
     one
    -0.06
     in
    -0.06
     पैर
    -0.06
     stewardship
    -0.06
    応募
    -0.06
    总是
    -0.06
    POSITIVE LOGITS
    改めて
    0.05
     deux
    0.05
     maksimal
    0.05
     Cleaner
    0.05
     два
    0.05
    uesthouse
    0.05
    ၂
    0.05
    inicial
    0.05
     parce
    0.05
     biogas
    0.05
    Activations Density 0.001%

    No Known Activations