© 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. 109838
    Prev
    Next
    INDEX
    Explanations

    numbers and costs

    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
     or
    -1.52
     first
    -1.49
     when
    -1.27
     creating
    -1.26
     usually
    -1.21
     most
    -1.17
     many
    -1.15
     created
    -1.14
     not
    -1.13
     time
    -1.13
    POSITIVE LOGITS
    􏰁
    1.36
    Furthermore
    1.34
    possibly
    1.23
     รวม
    1.20
     ORIGINAL
    1.16
    could
    1.15
    噙
    1.13
    籏
    1.13
    􏰀
    1.13
     intrigu
    1.12
    Activations Density 0.106%

    No Known Activations