© 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. 109833
    Prev
    Next
    INDEX
    Explanations

    mathematical operator names

    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
     建
    -0.75
     cookware
    -0.75
     gneiss
    -0.75
     Egyes
    -0.75
    мания
    -0.74
    weeb
    -0.73
    apost
    -0.72
    ridae
    -0.71
     Nectar
    -0.71
     $=
    -0.71
    POSITIVE LOGITS
    operatorname
    2.73
     dim
    1.11
     Rez
    1.10
     Tr
    1.00
     Re
    0.99
     Im
    0.95
     supp
    0.94
    Tr
    0.85
     ord
    0.83
    dim
    0.82
    Activations Density 0.071%

    No Known Activations