© 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. 22-GEMMASCOPE-RES-131K
    4. 12936
    Prev
    Next
    INDEX
    Explanations

    accessing object properties

    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
    わけではない
    -1.16
    来週
    -1.13
    attva
    -1.12
    つづく
    -1.09
    ことも
    -1.05
    為に
    -1.05
    方がいい
    -1.04
    の方も
    -1.04
    になれる
    -1.04
    の方に
    -1.02
    POSITIVE LOGITS
     lavanda
    1.31
    <bos>
    1.22
     گرفت
    1.09
    參考資料
    1.09
    cestor
    1.07
    動機
    1.07
    注意事項
    1.05
    hadores
    1.04
    Pilih
    1.04
     camere
    1.03
    Activations Density 0.003%

    No Known Activations