© 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. 118063
    Prev
    Next
    INDEX
    Explanations

    6

    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
     svilupp
    -0.06
     voller
    -0.06
     проек
    -0.06
    شون
    -0.06
     entwickelt
    -0.06
     nearly
    -0.05
    つつ
    -0.05
    で
    -0.05
     someth
    -0.05
     pylori
    -0.05
    POSITIVE LOGITS
    🫣
    0.07
    䞍
    0.07
     inconspicuous
    0.06
     পরিস্কার
    0.06
     liquides
    0.06
    udges
    0.06
     financial
    0.06
     unambiguous
    0.06
     reagents
    0.06
     bebas
    0.06
    Activations Density 0.013%

    No Known Activations