© 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. 117094
    Prev
    Next
    INDEX
    Explanations

    parsing code involving numbers

    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
     devenir
    -0.06
     রোগের
    -0.06
     চলবে
    -0.06
     buton
    -0.06
    translator
    -0.06
    🕒
    -0.06
     leur
    -0.06
    ✔️
    -0.06
    中文
    -0.06
    🕑
    -0.06
    POSITIVE LOGITS
     additions
    0.06
     Marrakech
    0.06
    ��
    0.05
    其中的
    0.05
     rarely
    0.05
     باقي
    0.05
     پہلی
    0.05
    When
    0.05
    emplate
    0.05
     कवाय
    0.05
    Activations Density 0.001%

    No Known Activations