© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128673
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    搜索引擎
    -0.06
    經營
    -0.06
     reforzar
    -0.06
     splice
    -0.06
    ,’’
    -0.06
     Costs
    -0.06
     hadn
    -0.06
    Costs
    -0.06
    SaveChanges
    -0.06
    ਹੁ
    -0.06
    POSITIVE LOGITS
     may
    0.07
     się
    0.06
     notable
    0.06
     alcune
    0.06
     varies
    0.06
    ়
    0.05
     some
    0.05
    sunset
    0.05
     spe
    0.05
     sometimes
    0.05
    Activations Density 0.007%

    No Known Activations