© 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. 40081
    Prev
    Next
    INDEX
    Explanations

    . , Q Detailed Gene Field The

    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
     our
    -1.33
     Reised
    -1.28
    CCIÓN
    -1.26
    ֺ
    -1.16
     my
    -1.16
     десер
    -1.13
     Кубка
    -1.12
    🩱
    -1.12
    ]),
    -1.10
    În
    -1.09
    POSITIVE LOGITS
    LoadScene
    1.24
    衞
    1.20
    龛
    1.19
     ユーザー
    1.18
    :
    1.16
     ファイル
    1.12
    ἀ
    1.11
    ̢
    1.09
    めます
    1.09
    翻攝
    1.09
    Activations Density 0.003%

    No Known Activations