© 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. 128487
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code structure

    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
     attualmente
    -0.07
     antes
    -0.06
     précéd
    -0.06
     inklusive
    -0.06
     entice
    -0.06
    此前
    -0.06
     darunter
    -0.06
    她
    -0.06
     её
    -0.06
     her
    -0.06
    POSITIVE LOGITS
     Иң
    0.06
     utilisateur
    0.06
    முதல்
    0.06
    哪个
    0.06
     Акысыз
    0.06
     промышлен
    0.06
    }=
    0.06
     божомол
    0.06
    क्ता
    0.06
    ियाँ
    0.06
    Activations Density 0.001%

    No Known Activations