© 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. 10-GEMMASCOPE-RES-131K
    7. 653
    Prev
    Next
    INDEX
    Explanations

    importing numpy and pandas

    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_10/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
     DIFFERENT
    -2.16
     verschillende
    -2.08
     trám
    -2.05
     Dinas
    -1.99
    seems
    -1.95
     dát
    -1.93
     horrid
    -1.90
    っているので
    -1.88
     diverses
    -1.87
     différentes
    -1.84
    POSITIVE LOGITS
     blatantly
    2.25
     new
    2.25
     while
    2.20
     came
    2.19
     unrelenting
    2.05
     undeniably
    2.02
     незавер
    1.99
     although
    1.98
     facilitating
    1.95
     this
    1.93
    Activations Density 0.029%

    No Known Activations