© 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. 118622
    Prev
    Next
    INDEX
    Explanations

    MEMORANDUM or OPINION

    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
     محاضرات
    -0.07
     महाराजा
    -0.07
     myös
    -0.06
     também
    -0.06
    yrıca
    -0.06
     också
    -0.06
     तसेच
    -0.06
    뷸
    -0.06
     tudi
    -0.06
     kaleidoscopic
    -0.06
    POSITIVE LOGITS
    Which
    0.08
     first
    0.07
     which
    0.07
     NC
    0.07
     all
    0.07
    <eos>
    0.07
    />
    0.06
     `
    0.06
     primera
    0.06
     md
    0.06
    Activations Density 0.001%

    No Known Activations