© 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. 10-GEMMASCOPE-RES-131K
    7. 110926
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    :
    -2.67
     If
    -1.95
    ものに
    -1.74
     incessant
    -1.73
    ので
    -1.71
     sparkly
    -1.70
     були
    -1.67
    isateurs
    -1.66
     épreuve
    -1.64
     improves
    -1.63
    POSITIVE LOGITS
     verkau
    2.44
     маленьких
    2.28
     podían
    2.05
    댔
    2.02
    re
    2.02
    they
    1.99
    豨
    1.97
    ではある
    1.94
    ⁛
    1.91
    時に
    1.90
    Activations Density 0.021%

    No Known Activations