© 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. 9642
    Prev
    Next
    INDEX
    Explanations

    probe

    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
     rampant
    -2.61
    ro
    -2.52
     pervasive
    -2.20
    ⟞
    -2.20
    ());
    -2.20
     slashing
    -2.09
     ‘
    -2.08
    と言
    -2.08
     sprawling
    -2.06
     newfound
    -2.06
    POSITIVE LOGITS
     didik
    2.73
     Ekonomi
    2.66
    榈
    2.52
     内衣
    2.52
    aged
    2.50
     pikir
    2.39
     Resmi
    2.38
     можешь
    2.38
    
    2.36
     saham
    2.34
    Activations Density 0.009%

    No Known Activations