© 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. 129786
    Prev
    Next
    INDEX
    Explanations

    normal/moderate

    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
    จัดการ
    -0.06
    ствием
    -0.06
     PLUGIN
    -0.06
     seamless
    -0.06
     අය
    -0.06
     irresponsible
    -0.06
     oops
    -0.06
     dices
    -0.06
     ऊंचाई
    -0.06
     supplement
    -0.06
    POSITIVE LOGITS
     normal
    0.08
    normal
    0.08
     limits
    0.07
     норма
    0.07
     four
    0.07
    正常
    0.07
     moderate
    0.07
     imposible
    0.07
     Normal
    0.07
     normale
    0.06
    Activations Density 0.049%

    No Known Activations