© 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. 117820
    Prev
    Next
    INDEX
    Explanations

    names

    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
    每次
    -0.06
    original
    -0.06
    Editor
    -0.06
    每
    -0.06
     SOCIETY
    -0.06
    Moreover
    -0.06
    報告
    -0.06
    ey
    -0.06
    Observers
    -0.06
     society
    -0.06
    POSITIVE LOGITS
     createState
    0.07
     help
    0.07
    可以在
    0.07
     सिलसिला
    0.06
     সেরে
    0.06
     known
    0.06
    친
    0.06
    کرا
    0.06
     நிதி
    0.06
     ISNI
    0.06
    Activations Density 0.011%

    No Known Activations