© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119685
    Prev
    Next
    INDEX
    Explanations

    aggregation and summation

    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
     reflects
    -0.07
     شاید
    -0.07
     surpasses
    -0.06
     வன
    -0.06
     depicts
    -0.06
     reflecting
    -0.06
     reflect
    -0.06
     उपलब्धता
    -0.06
     reaff
    -0.06
     reaffirm
    -0.06
    POSITIVE LOGITS
     روی
    0.06
     funzioni
    0.06
    procedures
    0.06
     accumulating
    0.06
    ensus
    0.06
     accumulations
    0.06
     Accum
    0.06
    sensors
    0.06
     procedures
    0.06
     aggreg
    0.06
    Activations Density 0.013%

    No Known Activations