© 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. 104299
    Prev
    Next
    INDEX
    Explanations

    array, sequence, item, eggs, replacement, name, Apple

    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
     about
    -1.05
    婭
    -1.02
    包括
    -0.93
    九月
    -0.93
    бирать
    -0.92
     Alkohol
    -0.91
     ГИ
    -0.91
    指定
    -0.91
     diberikan
    -0.90
    六年
    -0.88
    POSITIVE LOGITS
    カーテン
    1.01
    Благодаря
    0.96
     מכ
    0.94
     வெ
    0.92
    しましたが
    0.91
    Credentials
    0.91
    stdbool
    0.91
     zaradi
    0.91
    Determining
    0.88
     którego
    0.87
    Activations Density 0.004%

    No Known Activations