© 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. 128488
    Prev
    Next
    INDEX
    Explanations

    causal conjunctions

    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
     would
    -0.08
     have
    -0.07
     više
    -0.07
    不可能
    -0.07
    会被
    -0.07
     Number
    -0.07
     வேறு
    -0.07
     ما
    -0.07
     If
    -0.06
     wouldn
    -0.06
    POSITIVE LOGITS
    slightly
    0.06
     bridging
    0.06
     sowohl
    0.06
    mini
    0.06
     약간
    0.05
     اچھی
    0.05
    homemade
    0.05
    특히
    0.05
     dll
    0.05
     ihn
    0.05
    Activations Density 0.025%

    No Known Activations