© 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. 116531
    Prev
    Next
    INDEX
    Explanations

    Public Domain, Fair use

    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
    ঢ়
    -0.07
    只需
    -0.06
    ষে
    -0.06
     JDK
    -0.06
     produk
    -0.06
     rxjs
    -0.06
     vividly
    -0.06
     empir
    -0.06
    还能
    -0.06
     ještě
    -0.06
    POSITIVE LOGITS
     அனைத்து
    0.09
     all
    0.09
     모든
    0.07
     सभी
    0.07
     همه
    0.07
    所有
    0.06
    다른
    0.06
     many
    0.06
     جميع
    0.06
     všechny
    0.06
    Activations Density 0.001%

    No Known Activations