© 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. 118165
    Prev
    Next
    INDEX
    Explanations

    code: or tag syntax

    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
     Pakistan
    -0.06
    진다
    -0.06
    cox
    -0.05
     Countries
    -0.05
    grams
    -0.05
     hasta
    -0.05
     ordination
    -0.05
     Golgi
    -0.05
    aiti
    -0.05
     ক্ষমতার
    -0.05
    POSITIVE LOGITS
    ¿
    0.07
    hne
    0.06
     may
    0.06
     ভো
    0.06
    这些
    0.06
     зага
    0.06
    ുട
    0.06
    究竟
    0.06
     मतदारसंघात
    0.06
     भिन्न
    0.06
    Activations Density 0.003%

    No Known Activations