© 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. 130458
    Prev
    Next
    INDEX
    Explanations

    specific days and times for events

    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
     ubiquitous
    -0.07
     celebrity
    -0.07
     philanthropic
    -0.06
    勧め
    -0.06
     toured
    -0.06
     khuyến
    -0.06
     soulful
    -0.06
     participatory
    -0.06
     семина
    -0.06
    报名
    -0.06
    POSITIVE LOGITS
    บริเวณ
    0.06
     also
    0.06
     certaines
    0.06
    现状
    0.06
     existing
    0.06
     missed
    0.06
     அதன்
    0.06
     таксама
    0.06
     bazı
    0.06
     situasi
    0.05
    Activations Density 0.014%

    No Known Activations