© 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. 92999
    Prev
    Next
    INDEX
    Explanations

    actions causing trouble or extra effort

    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
    cún
    -1.22
     alcune
    -1.05
     vorige
    -0.98
     écrits
    -0.95
     vogliono
    -0.94
     gewisser
    -0.94
     gedachten
    -0.93
     alcuni
    -0.93
     sebel
    -0.92
     ロゴ
    -0.92
    POSITIVE LOGITS
     anymore
    1.79
     such
    1.20
     risk
    1.19
     risking
    1.17
     такое
    1.03
    èrent
    1.02
     такой
    1.01
     такую
    1.01
     further
    1.01
     any
    1.01
    Activations Density 0.021%

    No Known Activations