© 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. 117388
    Prev
    Next
    INDEX
    Explanations

    address: University Name

    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
     pomocą
    -0.06
     by
    -0.06
     носи
    -0.06
     कोणी
    -0.06
     लगभग
    -0.06
     wondrous
    -0.06
    ices
    -0.06
    τια
    -0.06
     ſ
    -0.06
    ிகளை
    -0.05
    POSITIVE LOGITS
     respectively
    0.06
    Car
    0.06
    pti
    0.06
    Continuing
    0.06
    坸
    0.06
     Несмотря
    0.06
    接下来
    0.06
    askets
    0.06
     brasileiros
    0.06
    Associate
    0.06
    Activations Density 0.002%

    No Known Activations