© 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. 10-GEMMASCOPE-RES-131K
    7. 130885
    Prev
    Next
    INDEX
    Explanations

    Company or License

    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_10/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
     vermutlich
    -1.16
     卧室
    -1.12
     поэтому
    -1.00
     désolés
    -0.99
     Поэтому
    -0.98
    Controllo
    -0.98
     up
    -0.97
     友
    -0.95
     even
    -0.94
    𝙣
    -0.93
    POSITIVE LOGITS
     were
    1.27
     iluminación
    1.20
     Créer
    1.19
     TResult
    1.18
     Paramètres
    1.17
     flexibilidad
    1.16
     miſ
    1.14
     écrire
    1.14
     bestaat
    1.13
     və
    1.12
    Activations Density 0.177%

    No Known Activations