© 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. 120240
    Prev
    Next
    INDEX
    Explanations

    code syntax and conditionals

    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
     jejich
    -0.06
     Liebe
    -0.06
     इस
    -0.06
     libert
    -0.06
     ক্যাম
    -0.06
     кантип
    -0.06
     ZIP
    -0.06
     ಯಾವ
    -0.06
    timezone
    -0.05
     Нау
    -0.05
    POSITIVE LOGITS
     sometimes
    0.06
     actually
    0.06
     making
    0.06
    ellate
    0.06
    ala
    0.06
    opolis
    0.06
    èn
    0.06
    ud
    0.06
     auch
    0.06
     equally
    0.06
    Activations Density 0.001%

    No Known Activations