© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36561
    Prev
    Next
    INDEX
    Explanations

    describing items or concepts

    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
     both
    -1.40
    both
    -1.22
     både
    -1.17
    Both
    -1.07
     and
    -1.02
    BOTH
    -1.02
    帖最后由
    -0.98
    ทั้ง
    -0.94
     दोनों
    -0.91
    去吧
    -0.89
    POSITIVE LOGITS
     which
    1.66
     rather
    1.45
    而言
    1.26
    而不是
    1.20
    sebagai
    1.16
    versen
    1.16
    
    1.03
     ולא
    0.97
     وليس
    0.96
     Waarom
    0.96
    Activations Density 0.101%

    No Known Activations