© 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. 109666
    Prev
    Next
    INDEX
    Explanations

    examples of apps and services

    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
    screenshots
    -0.98
    mainPanel
    -0.97
     ネタバレ
    -0.94
    btnNew
    -0.92
    linkedList
    -0.88
    kreises
    -0.88
     การ์ตูน
    -0.88
    tuy
    -0.87
     Technological
    -0.85
    шных
    -0.85
    POSITIVE LOGITS
     email
    2.08
     music
    2.00
     banking
    1.80
     games
    1.80
     Email
    1.79
     mail
    1.74
     video
    1.70
    email
    1.65
     chat
    1.59
     shopping
    1.59
    Activations Density 0.257%

    No Known Activations