© 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. 128399
    Prev
    Next
    INDEX
    Explanations

    prior

    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
     SOME
    -0.06
    つく
    -0.06
    SOME
    -0.06
     उपभो
    -0.06
     formerly
    -0.06
     Blak
    -0.06
     someone
    -0.06
     возле
    -0.06
    downcase
    -0.06
     Blackberry
    -0.06
    POSITIVE LOGITS
    ก่อน
    0.06
    prior
    0.06
    日で
    0.06
     prior
    0.06
     davantage
    0.06
     trước
    0.06
    ixin
    0.06
    rapp
    0.06
     PRIOR
    0.05
     early
    0.05
    Activations Density 0.054%

    No Known Activations