© 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. 118779
    Prev
    Next
    INDEX
    Explanations

    mathematical multiplication and operations

    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
    zaamheid
    -0.84
     faith
    -0.79
    ger
    -0.79
     Server
    -0.79
     Daß
    -0.78
     children
    -0.78
    してない
    -0.77
     hair
    -0.75
     Obwohl
    -0.75
     dogs
    -0.75
    POSITIVE LOGITS
     ×
    1.39
    cdot
    1.29
     times
    1.13
    ×
    1.04
    चाल
    0.96
    ⋅
    0.96
    times
    0.96
    ・
    0.94
    middot
    0.91
    engah
    0.90
    Activations Density 0.054%

    No Known Activations