© 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. 116857
    Prev
    Next
    INDEX
    Explanations

    probability distribution

    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
    選び
    -0.07
     chois
    -0.07
     थियो
    -0.06
     escolha
    -0.06
     Socio
    -0.06
     diversity
    -0.06
     chosen
    -0.06
    rikt
    -0.06
     Vil
    -0.06
    Forest
    -0.06
    POSITIVE LOGITS
     period
    0.06
     debut
    0.06
     enlisted
    0.06
     কয়েকটি
    0.06
     anteriores
    0.06
    pril
    0.06
     ఉండ
    0.06
     രണ്ട്
    0.06
     debuted
    0.06
     периода
    0.06
    Activations Density 0.005%

    No Known Activations