© 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. 117945
    Prev
    Next
    INDEX
    Explanations

    downloaded files

    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
     mendukung
    -0.07
     acredito
    -0.07
    0
    -0.06
    python
    -0.06
     asbestos
    -0.06
    有一些
    -0.06
     arb
    -0.06
    arb
    -0.06
    非洲
    -0.06
    ラボ
    -0.06
    POSITIVE LOGITS
     weder
    0.07
    ixar
    0.06
     neither
    0.06
     टेम्प
    0.06
     area
    0.06
     AREAS
    0.06
     to
    0.06
    Areas
    0.06
    portions
    0.06
     передба
    0.06
    Activations Density 0.005%

    No Known Activations