© 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. 130245
    Prev
    Next
    INDEX
    Explanations

    file paths and programming libraries

    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
     transportation
    -0.07
     रीठा
    -0.07
     facilitating
    -0.06
     বিনা
    -0.06
     disseminating
    -0.06
     Transportation
    -0.06
    ейчас
    -0.06
     বিষয়ক
    -0.06
     more
    -0.06
     preparatory
    -0.06
    POSITIVE LOGITS
     follows
    0.06
    标志
    0.06
    Ainsi
    0.06
    激情
    0.06
     SDA
    0.05
    ColumnHeaders
    0.05
    ┇
    0.05
     thus
    0.05
    ocardial
    0.05
    outputText
    0.05
    Activations Density 0.003%

    No Known Activations