© 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. 130461
    Prev
    Next
    INDEX
    Explanations

    constraints after subject, the, or cost

    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
     paying
    -0.06
     dla
    -0.06
     administrative
    -0.06
    付费
    -0.06
    administrative
    -0.06
     Paying
    -0.05
    so
    -0.05
     Kusum
    -0.05
    getDefault
    -0.05
     kinds
    -0.05
    POSITIVE LOGITS
     également
    0.07
     Constraints
    0.07
     pleine
    0.07
     constraints
    0.07
    Constraints
    0.07
     compatriots
    0.06
    constraints
    0.06
     también
    0.06
     factores
    0.06
     времена
    0.06
    Activations Density 0.005%

    No Known Activations