© 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. 119606
    Prev
    Next
    INDEX
    Explanations

    based on the novel

    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
     bookshelf
    -0.06
     chees
    -0.06
    卧室
    -0.06
     религи
    -0.06
    ゲ
    -0.06
     trustee
    -0.06
     po
    -0.06
     Trustee
    -0.06
     ఇతర
    -0.06
     spesso
    -0.06
    POSITIVE LOGITS
     more
    0.07
     문제가
    0.06
    ებით
    0.06
     continuing
    0.06
     calmer
    0.06
    lebih
    0.06
     Matt
    0.06
     substandard
    0.06
     continuando
    0.06
     melanjutkan
    0.06
    Activations Density 0.014%

    No Known Activations