© 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. 109865
    Prev
    Next
    INDEX
    Explanations

    System.Web, System.Data, System.Windows

    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
    せよ
    -1.05
     cause
    -0.98
     patient
    -0.92
    顯
    -0.89
     miejs
    -0.88
    _{{\
    -0.85
     trivial
    -0.84
     unex
    -0.83
     obvious
    -0.82
     During
    -0.82
    POSITIVE LOGITS
     kasa
    0.94
     fahren
    0.94
    getting
    0.93
     gof
    0.93
     ayur
    0.91
     afront
    0.91
    ANDROID
    0.90
    nowu
    0.89
     kompak
    0.89
     revolver
    0.87
    Activations Density 0.009%

    No Known Activations