© 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. 119354
    Prev
    Next
    INDEX
    Explanations

    programming modifiers

    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
     this
    -0.07
     मुखर्जी
    -0.06
     such
    -0.06
    =’
    -0.06
     fuller
    -0.05
     more
    -0.05
    更大
    -0.05
    更加
    -0.05
     stejně
    -0.05
    :
    -0.05
    POSITIVE LOGITS
    さんも
    0.07
    iquen
    0.07
     можно
    0.06
     мають
    0.06
     Estimation
    0.06
     знают
    0.06
     प्रेरणात्मक
    0.06
     etc
    0.06
     seront
    0.06
     მათი
    0.06
    Activations Density 0.011%

    No Known Activations