© 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. 119053
    Prev
    Next
    INDEX
    Explanations

    how policies, the exercise, phone phoneme, My Stream, two times, micro economics

    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
     আমি
    -0.08
     definitiv
    -0.07
    都被
    -0.07
     ప్రముఖ
    -0.07
     clairement
    -0.06
    Either
    -0.06
     ਨਹੀਂ
    -0.06
    fought
    -0.06
    waar
    -0.06
     uplink
    -0.06
    POSITIVE LOGITS
     manual
    0.06
    manual
    0.06
     three
    0.06
    분을
    0.05
     ел
    0.05
    ^{*}\
    0.05
     dislocation
    0.05
    लाल
    0.05
     জনগণকে
    0.05
     choć
    0.05
    Activations Density 0.092%

    No Known Activations