© 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. 118083
    Prev
    Next
    INDEX
    Explanations

    place names and adjectives

    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
    Companion
    -0.06
     eventdata
    -0.06
     companions
    -0.06
    であるが
    -0.06
     Companion
    -0.06
     teorie
    -0.06
    čný
    -0.06
    领域
    -0.06
    キーワード
    -0.05
    anbul
    -0.05
    POSITIVE LOGITS
     quickest
    0.07
    মাম
    0.06
     fastest
    0.06
     kinderg
    0.06
     सीआर
    0.06
    vers
    0.06
     maths
    0.06
     vers
    0.06
     प्रथम
    0.06
    oprop
    0.06
    Activations Density 0.024%

    No Known Activations