© 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. 118551
    Prev
    Next
    INDEX
    Explanations

    number of abundance

    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
    各种
    -0.08
     informasjon
    -0.08
    組み
    -0.07
     información
    -0.07
    情報
    -0.07
     szybko
    -0.07
    কলকাতা
    -0.06
     احتمال
    -0.06
     Якщо
    -0.06
    如果是
    -0.06
    POSITIVE LOGITS
     that
    0.08
     which
    0.08
    My
    0.06
    3
    0.06
     it
    0.06
     hashing
    0.06
    2
    0.06
    that
    0.06
    Tr
    0.06
     usable
    0.06
    Activations Density 0.006%

    No Known Activations