© 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. 127186
    Prev
    Next
    INDEX
    Explanations

    recreate

    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
    \
    -3.23
    }$
    -2.50
     et
    -2.31
    man
    -2.22
    
    -2.11
    瓩
    -2.09
     This
    -2.08
    ía
    -2.06
     необходимо
    -2.05
     eld
    -2.05
    POSITIVE LOGITS
     “[
    2.95
     “
    2.45
     “(
    2.38
    罌
    2.23
     (“
    2.23
    i
    2.11
     放題
    2.05
    阇
    2.03
    涣
    2.03
     They
    1.94
    Activations Density 0.003%

    No Known Activations