© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130801
    Prev
    Next
    INDEX
    Explanations

    units, currency, or specific quantities

    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
    పాల
    -0.07
     distingu
    -0.06
     distinguishing
    -0.06
     distinguishes
    -0.06
     особен
    -0.06
     distin
    -0.06
     distinguer
    -0.06
     nucleic
    -0.06
    Outstanding
    -0.06
    నాల
    -0.06
    POSITIVE LOGITS
     amount
    0.07
     poprzez
    0.07
     बढ़ोतरी
    0.06
     Deposit
    0.06
     deposit
    0.06
     통한
    0.06
     INFORM
    0.06
     tsh
    0.06
     Amount
    0.06
     keresztül
    0.06
    Activations Density 0.002%

    No Known Activations