© 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. 118255
    Prev
    Next
    INDEX
    Explanations

    until her

    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
    ִ
    -0.06
     аж
    -0.06
     tenor
    -0.06
     inspirations
    -0.06
    彻底
    -0.06
     অভ্যাস
    -0.05
     so
    -0.05
     radically
    -0.05
     Brill
    -0.05
    -
    -0.05
    POSITIVE LOGITS
     nama
    0.07
     jedna
    0.06
     etwa
    0.06
     Nama
    0.06
     algum
    0.06
     nouveaux
    0.06
     शुक्र
    0.06
    antara
    0.06
    در
    0.06
     ಭೂ
    0.06
    Activations Density 0.012%

    No Known Activations