© 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. 128434
    Prev
    Next
    INDEX
    Explanations

    signal brightness

    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
     Одна
    -0.07
     xâm
    -0.07
    反應
    -0.07
     count
    -0.06
     আন্দ
    -0.06
     Counts
    -0.06
     Alemanha
    -0.06
     Count
    -0.06
     EXPECT
    -0.06
    count
    -0.06
    POSITIVE LOGITS
     olabilir
    0.06
     zacz
    0.06
     Verfahren
    0.06
    dragging
    0.06
     начина
    0.06
     accentuated
    0.05
     many
    0.05
    iteration
    0.05
     vara
    0.05
     muchos
    0.05
    Activations Density 0.001%

    No Known Activations