© 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. 130268
    Prev
    Next
    INDEX
    Explanations

    Airbus A380

    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
     already
    -0.07
     அடையாளம்
    -0.07
     sudah
    -0.07
    Honestly
    -0.07
     Honestly
    -0.07
     sebelum
    -0.06
     असामान्य
    -0.06
     እንደ
    -0.06
     আমাকে
    -0.06
     literalmente
    -0.06
    POSITIVE LOGITS
     éstos
    0.06
     sometimes
    0.06
    Discussion
    0.06
    জনিত
    0.06
     discussion
    0.06
    bö
    0.06
    เยี่ยม
    0.06
     other
    0.06
    ارع
    0.06
     اخرى
    0.06
    Activations Density 0.001%

    No Known Activations