© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65069
    Prev
    Next
    INDEX
    Explanations

    into a duration of time

    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_10/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
     to
    -1.80
     Thursday
    -1.63
    {
    -1.59
    </sub>
    -1.56
     Friday
    -1.55
    </i>
    -1.55
     other
    -1.52
     Wednesday
    -1.51
     has
    -1.49
    问道
    -1.49
    POSITIVE LOGITS
    Отзыв
    1.66
    ،
    1.45
    コロナ禍
    1.45
    嵓
    1.41
    ,
    1.39
    鳏
    1.38
     炒め
    1.37
    祈り
    1.37
    Доку
    1.35
    久しぶりの
    1.34
    Activations Density 0.009%

    No Known Activations