© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75148
    Prev
    Next
    INDEX
    Explanations

    dramatically/drastically changing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    黽
    -1.61
    子は
    -1.56
     humeur
    -1.53
     escalada
    -1.52
    ⑉
    -1.46
     水墨
    -1.46
     дуже
    -1.46
    ائدة
    -1.45
    鼇
    -1.43
     پروفایل
    -1.42
    POSITIVE LOGITS
    '
    2.31
    T
    1.83
     different
    1.66
    ro
    1.63
    V
    1.59
     istnie
    1.54
     the
    1.52
    la
    1.52
    `
    1.49
    H
    1.46
    Activations Density 0.038%

    No Known Activations