© 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. 130417
    Prev
    Next
    INDEX
    Explanations

    names and descriptions

    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
     વિશે
    -0.07
    が見
    -0.06
     Dane
    -0.06
    𝐦
    -0.06
    解析
    -0.06
     эфи
    -0.06
    馴染
    -0.06
    Types
    -0.06
    素敵
    -0.06
    kinds
    -0.06
    POSITIVE LOGITS
     resultant
    0.08
    整个
    0.06
     How
    0.06
     resulting
    0.06
     მთ
    0.06
     MANUFACTURING
    0.06
     a
    0.06
     seluruh
    0.05
     celý
    0.05
     Maio
    0.05
    Activations Density 0.001%

    No Known Activations