© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 675
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
     also
    -1.64
     également
    -1.52
     también
    -1.48
     també
    -1.35
     також
    -1.32
     arī
    -1.28
     также
    -1.27
     agujero
    -1.22
     trovato
    -1.22
    InjectAttribute
    -1.22
    POSITIVE LOGITS
     in
    2.16
    我怎么
    1.18
    お花
    1.17
    水着
    1.16
    旁邊
    1.14
    这几
    1.14
    確実に
    1.11
     چیز
    1.11
     their
    1.08
     despite
    1.07
    Activations Density 0.262%

    No Known Activations