© 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. 12491
    Prev
    Next
    INDEX
    Explanations

    contrasting qualifications after 'but'

    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
    lagen
    -0.94
     únicamente
    -0.85
    kości
    -0.83
     contextLoads
    -0.83
    jublj
    -0.82
    chtig
    -0.80
     ficou
    -0.80
    龠
    -0.80
     Lala
    -0.79
    lible
    -0.78
    POSITIVE LOGITS
     certainly
    1.92
     definitely
    1.52
     surely
    1.45
     will
    1.41
    Certainly
    1.37
     jedenfalls
    1.23
     Certainly
    1.22
    certainly
    1.21
     definately
    1.15
     certainement
    1.14
    Activations Density 0.024%

    No Known Activations