© 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. 120577
    Prev
    Next
    INDEX
    Explanations

    "effect of" / "in the" / "a" + noun

    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
     tych
    -0.05
     hybridized
    -0.05
    adjust
    -0.05
     Tiwari
    -0.05
     walks
    -0.05
    acci
    -0.05
     deletion
    -0.05
     wherever
    -0.05
     Debye
    -0.05
     ₹
    -0.05
    POSITIVE LOGITS
    謳
    0.07
    radical
    0.07
               
    0.06
    的的
    0.06
     ولد
    0.06
     в
    0.06
     in
    0.06
     beispielsweise
    0.06
     become
    0.06
    你说
    0.06
    Activations Density 0.001%

    No Known Activations