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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41070
    Prev
    Next
    INDEX
    Explanations

    words starting with Tr

    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
    8
    -3.36
    6
    -2.84
      
    -2.81
    3
    -2.73
    7
    -2.69
    9
    -2.58
    5
    -2.52
    や
    -2.50
    4
    -2.48
     неболь
    -2.44
    POSITIVE LOGITS
     书法
    2.52
     and
    2.36
    釙
    2.28
    ☆☆☆☆
    2.28
    咘
    2.27
     以上
    2.25
    ’
    2.25
     階段
    2.23
    月号
    2.22
    \
    2.22
    Activations Density 0.003%

    No Known Activations