© 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. 130116
    Prev
    Next
    INDEX
    Explanations

    counts of thousands or millions

    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
    Algun
    -0.06
     como
    -0.06
     někter
    -0.06
     ছয়
    -0.06
    いくつか
    -0.06
     seperti
    -0.06
    ப்பட்டி
    -0.06
    hiver
    -0.06
     Algunas
    -0.06
     annual
    -0.06
    POSITIVE LOGITS
    jahter
    0.06
     just
    0.06
     should
    0.06
    MAGIC
    0.06
    이니까
    0.06
    aknya
    0.06
     tracers
    0.06
     نیند
    0.06
     হতেই
    0.06
    ൃ
    0.06
    Activations Density 0.015%

    No Known Activations