© 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. 129834
    Prev
    Next
    INDEX
    Explanations

    layering piece

    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
     separating
    -0.06
    指定
    -0.06
     expire
    -0.06
     differentiate
    -0.06
    рем
    -0.06
     Mab
    -0.05
     conditions
    -0.05
     نسب
    -0.05
     Amounts
    -0.05
    Particles
    -0.05
    POSITIVE LOGITS
     utilidad
    0.07
     Supplementary
    0.07
     complementary
    0.07
    redund
    0.07
     supplement
    0.07
     innermost
    0.06
     complementarity
    0.06
     først
    0.06
     interle
    0.06
    เสริม
    0.06
    Activations Density 0.072%

    No Known Activations