© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128974
    Prev
    Next
    INDEX
    Explanations

    research or study findings

    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
     അദ്ദേഹ
    -0.07
     சுண்ணா
    -0.07
    他们
    -0.06
     還
    -0.06
     çoğu
    -0.06
    早就
    -0.06
     சிகிச்சை
    -0.06
     stejně
    -0.06
     нынеш
    -0.06
    数据
    -0.06
    POSITIVE LOGITS
     создание
    0.07
     that
    0.06
     मैं
    0.06
     мной
    0.06
     creates
    0.06
    myst
    0.06
     creazione
    0.06
    我知道
    0.06
    ുടെ
    0.06
     creada
    0.06
    Activations Density 0.028%

    No Known Activations