© 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. 79928
    Prev
    Next
    INDEX
    Explanations

    programming code and multilingual texts

    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
    圖片
    -0.93
    キング
    -0.89
     NOD
    -0.88
    ⽬
    -0.88
     skå
    -0.88
    ámicas
    -0.86
    電子
    -0.85
     moglie
    -0.85
    Влади
    -0.85
     malaysia
    -0.84
    POSITIVE LOGITS
    inqui
    1.01
     Warenkorb
    0.87
     their
    0.85
     napisał
    0.84
    ですか
    0.84
    さんと
    0.84
     повіт
    0.83
    および
    0.82
    𝙞
    0.81
     može
    0.80
    Activations Density 0.038%

    No Known Activations