© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118847
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     대부분
    -0.07
     اکثر
    -0.06
     छह
    -0.06
     無
    -0.06
    నాన్ని
    -0.06
     CHILD
    -0.06
     pernicious
    -0.06
    六
    -0.06
     नहीं
    -0.06
    情報の
    -0.06
    POSITIVE LOGITS
     वायर
    0.06
     sollen
    0.06
     showed
    0.06
    _____
    0.06
    都要
    0.06
     betyder
    0.06
    用意
    0.06
    清楚
    0.06
     $^{\
    0.06
     through
    0.05
    Activations Density 0.002%

    No Known Activations