© 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. 116220
    Prev
    Next
    INDEX
    Explanations

    Entity types or code structure

    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
    其
    -0.07
     vital
    -0.06
     эксплуатации
    -0.06
    ≥
    -0.06
     характеристи
    -0.06
     Therefore
    -0.06
     essential
    -0.06
    Bold
    -0.06
     usa
    -0.06
     второй
    -0.06
    POSITIVE LOGITS
     تغير
    0.06
     ganz
    0.06
    ிகளில்
    0.06
     separately
    0.06
    ினார்கள்
    0.06
     remained
    0.06
    اهای
    0.06
     propagation
    0.06
    +/-
    0.06
     kvar
    0.05
    Activations Density 0.001%

    No Known Activations