© 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. 130418
    Prev
    Next
    INDEX
    Explanations

    X/Y ratios and symmetric points

    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
    
    -0.06
     dispute
    -0.06
    一行
    -0.06
     Yangtze
    -0.06
    दर्शन
    -0.06
    将被
    -0.06
     lengthwise
    -0.06
     उल
    -0.06
    arker
    -0.06
     Sélection
    -0.06
    POSITIVE LOGITS
     each
    0.06
     comparatively
    0.06
     computationally
    0.06
     somewhat
    0.06
    不必
    0.06
     soz
    0.06
     indip
    0.06
    Each
    0.06
     слабо
    0.06
    each
    0.06
    Activations Density 0.027%

    No Known Activations