© 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. 11173
    Prev
    Next
    INDEX
    Explanations

    event handlers and code

    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
    由于
    -1.68
    其他
    -1.63
    的
    -1.62
    因为
    -1.60
    最大
    -1.59
    即使
    -1.58
    t
    -1.55
    这些
    -1.51
    一个
    -1.51
    es
    -1.48
    POSITIVE LOGITS
    ܃
    1.77
    ではまた
    1.63
    をします
    1.59
    hysema
    1.57
    総評
    1.55
    ஂ
    1.55
    Ꮚ
    1.54
    Ꮸ
    1.52
    鳧
    1.52
     vám
    1.52
    Activations Density 0.000%

    No Known Activations