© 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. 118002
    Prev
    Next
    INDEX
    Explanations

    dependent behavior detection

    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
     आते
    -0.07
    razol
    -0.07
     distinctive
    -0.06
     changeable
    -0.06
     اليوم
    -0.06
     ವಿಶ
    -0.06
    when
    -0.06
     요소
    -0.06
    defining
    -0.06
    лябин
    -0.06
    POSITIVE LOGITS
    ↵↵↵
    0.07
    ​​
    0.06
    🎅
    0.06
     Croatia
    0.06
    !
    0.05
    }}\
    0.05
    /
    0.05
    |}\
    0.05
     systemat
    0.05
     ပြ
    0.05
    Activations Density 0.054%

    No Known Activations