© 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. 60193
    Prev
    Next
    INDEX
    Explanations

    become

    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
     but
    -1.91
     such
    -1.79
     both
    -1.67
     then
    -1.60
    こうして
    -1.59
    そういった
    -1.55
    それだけ
    -1.53
     there
    -1.52
     here
    -1.50
    たまたま
    -1.50
    POSITIVE LOGITS
    荩
    1.74
    
    1.74
     аккура
    1.67
    ），
    1.66
    ѣмъ
    1.61
     minder
    1.60
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.60
     anderen
    1.58
    |
    1.56
    Ⲉ
    1.56
    Activations Density 0.020%

    No Known Activations