© 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. 116459
    Prev
    Next
    INDEX
    Explanations

    duration, time, or timing

    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
     after
    -0.07
     setelah
    -0.06
     뿐
    -0.06
     baada
    -0.06
     fiind
    -0.06
    หลังจาก
    -0.05
     yun
    -0.05
    뿐
    -0.05
    after
    -0.05
     ঘন্টা
    -0.05
    POSITIVE LOGITS
     freestyle
    0.07
     draped
    0.07
     경우는
    0.06
     fructose
    0.06
     Bruck
    0.06
     ressent
    0.06
     osią
    0.06
     올해
    0.06
     Međutim
    0.06
     दिस
    0.06
    Activations Density 0.002%

    No Known Activations