© 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. 117754
    Prev
    Next
    INDEX
    Explanations

    Robert Mueller Rosenstein

    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
    泄
    -0.06
     सीता
    -0.06
    proper
    -0.06
     törté
    -0.06
     add
    -0.06
    native
    -0.06
     unprofessional
    -0.06
     separately
    -0.06
    这份
    -0.06
     improper
    -0.06
    POSITIVE LOGITS
     menyelesaikan
    0.07
     военных
    0.06
    ंकर
    0.06
     military
    0.06
    Algorithms
    0.06
     menang
    0.06
     reported
    0.06
     রকম
    0.06
     ネイビー
    0.06
     dominion
    0.06
    Activations Density 0.003%

    No Known Activations