© 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. 120127
    Prev
    Next
    INDEX
    Explanations

    code includes and file paths

    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
     Make
    -0.07
     milion
    -0.07
     millions
    -0.07
    🤠
    -0.07
     When
    -0.06
     mysticism
    -0.06
    道具
    -0.06
    aparikkh
    -0.06
     миллионов
    -0.06
     What
    -0.06
    POSITIVE LOGITS
     Ryzen
    0.06
    зывать
    0.06
     সৌম
    0.06
     Corse
    0.05
     Wendell
    0.05
     xe
    0.05
     মর্ম
    0.05
     остальные
    0.05
     春
    0.05
     klasse
    0.05
    Activations Density 0.001%

    No Known Activations