© 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. 75317
    Prev
    Next
    INDEX
    Explanations

    latex environments

    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
    などが
    -1.98
    骉
    -1.91
    なども
    -1.82
    蕷
    -1.82
    琑
    -1.65
    歺
    -1.62
    せっかく
    -1.61
    a
    -1.61
    푆
    -1.58
    begin
    -1.56
    POSITIVE LOGITS
    {
    2.80
    硖
    2.66
     \
    2.64
    ].
    2.19
    ।
    1.97
     點
    1.87
    ine
    1.84
    ``
    1.84
    .\
    1.80
    ';
    1.76
    Activations Density 0.001%

    No Known Activations