© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130727
    Prev
    Next
    INDEX
    Explanations

    regardless/majority/all

    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
     one
    -0.06
     অন্যতম
    -0.06
     ök
    -0.06
     unsuccessfully
    -0.06
     eki
    -0.06
     أحد
    -0.06
     Knicks
    -0.05
     असली
    -0.05
     یکی
    -0.05
     into
    -0.05
    POSITIVE LOGITS
    regardless
    0.07
     অধিকাংশ
    0.07
     regardless
    0.07
    Regardless
    0.07
     hầu
    0.07
    全ての
    0.07
     большинство
    0.06
     Regardless
    0.06
     अधिकांश
    0.06
    Todas
    0.06
    Activations Density 0.007%

    No Known Activations