© 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. 130979
    Prev
    Next
    INDEX
    Explanations

    code comments and namespaces

    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
     कोलकाता
    -0.07
    iume
    -0.07
    ज़र
    -0.06
     permet
    -0.06
    样子
    -0.06
     নিকটে
    -0.06
    ushan
    -0.06
     Dewan
    -0.06
     upstream
    -0.06
     ανάπτυ
    -0.06
    POSITIVE LOGITS
    .
    0.06
    should
    0.05
     also
    0.05
    could
    0.05
    impact
    0.05
    ፀ
    0.05
    would
    0.05
     impact
    0.05
    run
    0.05
    some
    0.05
    Activations Density 0.002%

    No Known Activations