© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119141
    Prev
    Next
    INDEX
    Explanations

    happened this week

    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
     nutzt
    -0.07
     destek
    -0.06
     مرکز
    -0.06
     digunakan
    -0.06
     Chung
    -0.06
     하나의
    -0.06
     nutzen
    -0.06
     просто
    -0.06
     genutzt
    -0.06
     사용할
    -0.06
    POSITIVE LOGITS
     materially
    0.06
     similar
    0.06
    🔙
    0.06
     unjust
    0.06
    内で
    0.06
    ก็
    0.06
     incorrectly
    0.06
     unnecessary
    0.06
     unknowingly
    0.06
     avoidable
    0.06
    Activations Density 0.021%

    No Known Activations