© 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. 129343
    Prev
    Next
    INDEX
    Explanations

    competitive price

    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
     جائے۔
    -0.06
    ందించ
    -0.06
     Clean
    -0.06
    通过
    -0.06
    िकेट
    -0.06
    सुद्धा
    -0.06
    clean
    -0.05
    Clean
    -0.05
     essences
    -0.05
     conversations
    -0.05
    POSITIVE LOGITS
    前的
    0.07
    льо
    0.06
     الطيب
    0.06
     redemption
    0.06
    有点
    0.06
     това
    0.06
    WHM
    0.06
    '-
    0.06
    lbl
    0.06
     brut
    0.06
    Activations Density 0.001%

    No Known Activations