© 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. 130342
    Prev
    Next
    INDEX
    Explanations

    programming and software development

    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
     vários
    -0.07
     varias
    -0.07
    几种
    -0.07
    几个
    -0.07
    ಸು
    -0.06
     várias
    -0.06
    这些
    -0.06
    いくつかの
    -0.06
     কতকগুলি
    -0.06
    Utf
    -0.06
    POSITIVE LOGITS
     igen
    0.06
    যখন
    0.06
     magnificent
    0.06
     ensuring
    0.06
    VIDEO
    0.05
    ybės
    0.05
    Allocate
    0.05
     ideal
    0.05
     Pepsi
    0.05
    分配
    0.05
    Activations Density 0.002%

    No Known Activations