© 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. 117799
    Prev
    Next
    INDEX
    Explanations

    programming utilities grep find awk

    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
     популяр
    -0.07
     সঞ্চ
    -0.06
     онлайн
    -0.06
    ดัง
    -0.06
     witty
    -0.06
     LGBTQ
    -0.06
    EVERY
    -0.06
    Before
    -0.06
    Including
    -0.06
     এটি
    -0.06
    POSITIVE LOGITS
     named
    0.06
     two
    0.06
     three
    0.06
     Botswana
    0.06
     airports
    0.05
    ména
    0.05
    rarea
    0.05
     faci
    0.05
    벳
    0.05
     confirm
    0.05
    Activations Density 0.001%

    No Known Activations