© 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. 572
    Prev
    Next
    INDEX
    Explanations

    variable suffixes

    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
    ！”
    -1.66
     attravers
    -1.64
    жены
    -1.60
    重要的
    -1.55
    ść
    -1.54
    })$.
    -1.49
     spirituale
    -1.46
    變成
    -1.45
     avviene
    -1.44
     giapp
    -1.43
    POSITIVE LOGITS
     still
    1.54
     of
    1.51
     
    1.42
    掲示
    1.38
     seinen
    1.36
     is
    1.33
     STILL
    1.31
     finally
    1.27
    a
    1.27
    重ね
    1.24
    Activations Density 0.009%

    No Known Activations