© 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. 83968
    Prev
    Next
    INDEX
    Explanations

    names ending in ies, ays, eis

    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
    キュー
    -0.74
     mennes
    -0.73
    邂
    -0.71
     participate
    -0.71
    qin
    -0.71
     steder
    -0.68
     forfatter
    -0.68
    応援
    -0.68
    ditions
    -0.68
    菜单
    -0.68
    POSITIVE LOGITS
    Zutaten
    0.88
    Gibt
    0.82
    Doch
    0.78
    Qualität
    0.76
    kket
    0.76
    gangs
    0.76
    Einstellungen
    0.76
    Ռ
    0.73
     Inflate
    0.73
     Jur
    0.73
    Activations Density 0.025%

    No Known Activations