© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110609
    Prev
    Next
    INDEX
    Explanations

    common verb phrases

    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
     реально
    -1.24
    Yeah
    -0.96
     creatividad
    -0.93
    遽
    -0.92
    awesome
    -0.91
     teljes
    -0.91
     tersebut
    -0.90
    tabBar
    -0.89
     explicación
    -0.89
    yeah
    -0.89
    POSITIVE LOGITS
    кновен
    1.17
     golos
    1.05
     ordentlich
    0.96
     queer
    0.94
    Здравствуйте
    0.91
     Queer
    0.90
     fastening
    0.87
     passenden
    0.87
     beginning
    0.86
     fastened
    0.86
    Activations Density 0.024%

    No Known Activations