© 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. 110589
    Prev
    Next
    INDEX
    Explanations

    code and conditional logic

    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
     then
    -1.31
     but
    -1.23
     GlobalKey
    -0.91
    缰
    -0.91
    でしたが
    -0.90
    だったが
    -0.90
    jkl
    -0.90
    stunning
    -0.87
    tabilidad
    -0.85
     знали
    -0.85
    POSITIVE LOGITS
     insistent
    0.86
     وہ
    0.81
     artikkelen
    0.79
    かは
    0.79
     avancée
    0.78
    トイ
    0.78
     оформления
    0.78
     یہ
    0.78
     оформление
    0.78
     إلى
    0.75
    Activations Density 0.006%

    No Known Activations