Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 263
    Prev
    Next
    INDEX
    Explanations

    control flow and continuity equation

    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
    Planner
    -0.77
     Shanks
    -0.74
     too
    -0.71
     Maret
    -0.69
     concor
    -0.68
    的角色
    -0.68
    Spi
    -0.68
    ↑↑↑
    -0.68
     tori
    -0.67
     useHistory
    -0.66
    POSITIVE LOGITS
     control
    1.27
    Control
    1.14
    control
    1.12
     Control
    1.05
    ontrol
    1.03
    providedIn
    0.99
     steady
    0.98
    Mass
    0.95
     mass
    0.94
    steady
    0.90
    Activations Density 0.006%

    No Known Activations