© 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. 119131
    Prev
    Next
    INDEX
    Explanations

    gate, base, terminal

    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
    ಗೊಳ್ಳ
    -0.07
     réellement
    -0.06
    byter
    -0.06
     footpath
    -0.06
    effectively
    -0.06
     foot
    -0.06
    apod
    -0.06
    प्रकारे
    -0.05
    ক্ষণে
    -0.05
    ittal
    -0.05
    POSITIVE LOGITS
    时期
    0.06
     prih
    0.06
    Several
    0.06
    ຫຼາຍ
    0.06
     IST
    0.06
     rescue
    0.06
     upbeat
    0.06
    Raised
    0.05
     Nieder
    0.05
     田
    0.05
    Activations Density 0.001%

    No Known Activations