© 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. 119249
    Prev
    Next
    INDEX
    Explanations

    retrospective analysis/review

    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
     ønsker
    -0.06
     Dade
    -0.06
     বাস্তব
    -0.06
     частью
    -0.06
    ┕
    -0.06
    eep
    -0.06
    ordine
    -0.06
     এন্টি
    -0.06
     réelle
    -0.06
     rack
    -0.05
    POSITIVE LOGITS
     quatre
    0.07
     dựa
    0.07
    根据
    0.07
    根據
    0.06
     guid
    0.06
     desider
    0.06
     bly
    0.06
    依据
    0.06
    textFont
    0.06
    consent
    0.06
    Activations Density 0.005%

    No Known Activations