© 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. 129348
    Prev
    Next
    INDEX
    Explanations

    court proceedings

    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
     ऑफ
    -0.06
     dość
    -0.06
     
    -0.06
    …,
    -0.05
     fairly
    -0.05
     reac
    -0.05
     dubious
    -0.05
     slimy
    -0.05
    rů
    -0.05
    ลาด
    -0.05
    POSITIVE LOGITS
     каждый
    0.07
     equivalente
    0.06
    यहां
    0.06
     تفس
    0.06
    我们
    0.06
    youtu
    0.06
     karena
    0.06
    এটা
    0.06
     일부
    0.06
    因为
    0.06
    Activations Density 0.001%

    No Known Activations