© 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. 117735
    Prev
    Next
    INDEX
    Explanations

    TJ code markers

    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
     mesela
    -0.07
     প্রথম
    -0.07
     nhưng
    -0.07
     אבל
    -0.07
     должны
    -0.07
     например
    -0.06
     ولكن
    -0.06
    例如
    -0.06
    比如说
    -0.06
    但是
    -0.06
    POSITIVE LOGITS
     و
    0.06
     and
    0.06
    adic
    0.06
     as
    0.06
     व
    0.06
     combining
    0.05
     छ
    0.05
    ê
    0.05
    পাকিস্তান
    0.05
     Mc
    0.05
    Activations Density 0.003%

    No Known Activations