© 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. 34-GEMMASCOPE-RES-131K
    7. 50142
    Prev
    Next
    INDEX
    Explanations

    Kenne, Keen, Kean names

    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_34/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
     Janes
    -0.80
     principalement
    -0.77
    experience
    -0.75
     undefeated
    -0.75
     clear
    -0.74
    classmethod
    -0.74
    رسد
    -0.74
    嬈
    -0.73
    ctuation
    -0.72
     critica
    -0.71
    POSITIVE LOGITS
     observers
    0.82
    muth
    0.77
    ソフトウェア
    0.74
    ᱢ
    0.74
     Diaspora
    0.73
     elő
    0.71
    みてください
    0.67
     Meme
    0.67
     💗
    0.66
     tribunal
    0.66
    Activations Density 0.019%

    No Known Activations