© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129206
    Prev
    Next
    INDEX
    Explanations

    "Q: " or "Sub: "

    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
     வினை
    -0.06
     більше
    -0.06
     用
    -0.06
    navigations
    -0.06
     περισσότε
    -0.06
    Extend
    -0.06
     License
    -0.06
     بیشتری
    -0.06
    更多
    -0.06
     больше
    -0.06
    POSITIVE LOGITS
     protecting
    0.07
    自己在
    0.06
     idée
    0.06
     physico
    0.06
    InputBorder
    0.06
    rms
    0.06
     künstler
    0.06
     immovable
    0.06
    liss
    0.06
     стране
    0.06
    Activations Density 0.002%

    No Known Activations