© 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. 129910
    Prev
    Next
    INDEX
    Explanations

    integrated circuits density

    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
     Altogether
    -0.06
     recrystall
    -0.06
     trainee
    -0.06
    ╅
    -0.06
     Coulomb
    -0.06
     apprentice
    -0.06
     merged
    -0.06
     data
    -0.05
    Tesla
    -0.05
     kecamatan
    -0.05
    POSITIVE LOGITS
    typically
    0.07
    awa
    0.06
    being
    0.06
     Prand
    0.06
    采用
    0.06
    ціона
    0.06
     being
    0.06
    from
    0.06
    simple
    0.06
    कोई
    0.06
    Activations Density 0.018%

    No Known Activations