© 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. 40185
    Prev
    Next
    INDEX
    Explanations

    than usual

    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
    侥
    -1.02
     quia
    -1.02
    leggio
    -0.98
    uating
    -0.96
     remol
    -0.94
    
    -0.93
    kiwa
    -0.93
     naï
    -0.92
     Ө
    -0.91
    ydon
    -0.90
    POSITIVE LOGITS
     conventional
    1.29
     traditional
    1.08
     money
    1.07
    Having
    1.00
    現金
    0.95
    Using
    0.93
     costly
    0.93
     Eintritt
    0.91
    Only
    0.87
     expensive
    0.84
    Activations Density 0.052%

    No Known Activations