© 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. 120470
    Prev
    Next
    INDEX
    Explanations

    percentage values

    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
    เป็น
    -0.06
    这是
    -0.06
     nella
    -0.06
    這是
    -0.06
    ป็น
    -0.06
     เป็น
    -0.06
     હવે
    -0.06
     그러면은
    -0.06
     現在
    -0.06
     być
    -0.06
    POSITIVE LOGITS
     hedges
    0.06
     granulation
    0.06
    且
    0.06
     मुआवजे
    0.06
     instrument
    0.06
    friction
    0.06
     stationed
    0.05
    而不是
    0.05
    vit
    0.05
    w
    0.05
    Activations Density 0.001%

    No Known Activations