© 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. 120496
    Prev
    Next
    INDEX
    Explanations

    total or combined

    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
     then
    -0.06
     начал
    -0.06
    整个
    -0.06
     this
    -0.06
     not
    -0.06
     wisdom
    -0.06
     మొత్తం
    -0.06
     algo
    -0.06
     começa
    -0.06
    uto
    -0.06
    POSITIVE LOGITS
    ほしい
    0.07
    Without
    0.06
     تۆ
    0.06
    Versioning
    0.06
    ayos
    0.06
    Existence
    0.06
    enza
    0.06
    bei
    0.06
    Melitaea
    0.06
     ಹೆಸರು
    0.06
    Activations Density 0.004%

    No Known Activations