© 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. 118750
    Prev
    Next
    INDEX
    Explanations

    actions performed or controlled

    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
     необхід
    -0.08
     দরকার
    -0.07
     necesidad
    -0.07
     প্রয়োজন
    -0.07
     ভিডিও
    -0.07
     berikutnya
    -0.07
     даже
    -0.07
     addirittura
    -0.07
     bahkan
    -0.06
     حتی
    -0.06
    POSITIVE LOGITS
     first
    0.06
    只能
    0.06
     nač
    0.06
     त्रि
    0.06
     красный
    0.06
    只会
    0.06
     Al
    0.06
     only
    0.06
     svo
    0.05
     cei
    0.05
    Activations Density 0.039%

    No Known Activations