© 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. 129671
    Prev
    Next
    INDEX
    Explanations

    PRECEDENTIAL, data, tree, story, output, CBS, page

    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
     deft
    -0.06
     Современ
    -0.06
     microsoft
    -0.06
    ലാണ്
    -0.06
    Contains
    -0.06
     vehicular
    -0.06
    ↵
    -0.06
    contemporary
    -0.05
     तमाम
    -0.05
     envolvendo
    -0.05
    POSITIVE LOGITS
     actively
    0.06
     rõ
    0.06
    ಬಹುದ
    0.06
     biết
    0.06
     recommended
    0.06
     petition
    0.06
     historically
    0.06
    तरा
    0.05
    most
    0.05
    가
    0.05
    Activations Density 0.001%

    No Known Activations