© 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. 120123
    Prev
    Next
    INDEX
    Explanations

    additional / code / symbols

    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
    调节
    -0.07
    由于
    -0.06
     Optimization
    -0.06
     optimizes
    -0.06
     desag
    -0.06
    由於
    -0.06
    Globe
    -0.06
    दिशा
    -0.06
     optimizations
    -0.06
    year
    -0.06
    POSITIVE LOGITS
     zusätzlichen
    0.07
     additional
    0.07
     mortality
    0.07
     sobot
    0.07
     sparingly
    0.06
    additional
    0.06
    额外的
    0.06
     zvol
    0.06
    Additional
    0.06
     tambahan
    0.06
    Activations Density 0.001%

    No Known Activations