© 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. 128912
    Prev
    Next
    INDEX
    Explanations

    season six "other"

    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
    จาก
    -0.08
    后
    -0.07
     بعدها
    -0.07
     unforeseen
    -0.06
    로부터
    -0.06
     후에
    -0.06
     뒤
    -0.06
     från
    -0.06
    नोट
    -0.06
    pressure
    -0.05
    POSITIVE LOGITS
     اچھا
    0.06
     যেসব
    0.06
    사람
    0.06
    ෲ
    0.06
    batim
    0.06
     सप्त
    0.06
     crux
    0.06
     ロー
    0.06
    Ⲥ
    0.06
     oats
    0.06
    Activations Density 0.001%

    No Known Activations