© 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. 22-GEMMASCOPE-RES-131K
    7. 12357
    Prev
    Next
    INDEX
    Explanations

    energy and pensions

    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_22/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
     Nội
    -0.96
    ieuse
    -0.91
     decisive
    -0.90
     Người
    -0.87
     convincing
    -0.86
     aufmerksam
    -0.84
    ConfigureAwait
    -0.84
    を行います
    -0.84
    gensen
    -0.83
     rocks
    -0.83
    POSITIVE LOGITS
     without
    1.29
     but
    1.20
     только
    1.04
    "=>"
    1.02
    voer
    1.02
     فقط
    1.00
     вместо
    0.98
    ffee
    0.97
    шат
    0.94
     بدون
    0.94
    Activations Density 0.077%

    No Known Activations