© 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. 118786
    Prev
    Next
    INDEX
    Explanations

    "This invention""Nyhavn""Q:""Fast"

    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
    prising
    -0.07
     třeba
    -0.07
     ours
    -0.07
     наша
    -0.06
     our
    -0.06
     директора
    -0.06
    เช่น
    -0.06
     such
    -0.06
    标志
    -0.06
     ہمارا
    -0.06
    POSITIVE LOGITS
    ↵
    0.08
    reduction
    0.07
    💫
    0.07
     reduction
    0.07
    他的
    0.07
     একাধিক
    0.06
    ಬ್ಬ
    0.06
    两个
    0.06
     ஆகிய
    0.06
    ड़
    0.06
    Activations Density 0.001%

    No Known Activations