© 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. 120301
    Prev
    Next
    INDEX
    Explanations

    debugbar and profiler terms

    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
     Untold
    -0.06
     اي
    -0.06
    回应
    -0.06
     HAPP
    -0.06
     ଆ
    -0.05
    akin
    -0.05
     stutter
    -0.05
    Along
    -0.05
     Along
    -0.05
     ਅ
    -0.05
    POSITIVE LOGITS
    情報
    0.07
     정보
    0.07
     like
    0.07
     secteurs
    0.07
     тощо
    0.06
     ತೋರಿಸ
    0.06
     wastewater
    0.06
     रहेंगे
    0.06
    情報を
    0.06
     sharps
    0.06
    Activations Density 0.004%

    No Known Activations