© 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. 118110
    Prev
    Next
    INDEX
    Explanations

    gene, protein, or compound names

    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
     अन्य
    -0.07
     другого
    -0.06
    已經
    -0.06
    的其他
    -0.06
    专门
    -0.06
    已经
    -0.06
    Already
    -0.06
     altra
    -0.06
     third
    -0.06
     내가
    -0.06
    POSITIVE LOGITS
     baza
    0.06
     crowd
    0.06
     comenzamos
    0.06
    或是
    0.06
     regiments
    0.06
     disappointed
    0.06
     scepticism
    0.05
    িব
    0.05
     dissatisfied
    0.05
     स्टेटमेंट
    0.05
    Activations Density 0.005%

    No Known Activations