© 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. 39904
    Prev
    Next
    INDEX
    Explanations

    testimonials and feedback

    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
     but
    -1.17
    strado
    -1.06
    ajā
    -0.94
    Mutagenicity
    -0.92
     if
    -0.91
    MongoClient
    -0.88
     RATIO
    -0.88
    Ratio
    -0.87
     eikä
    -0.86
    answer
    -0.85
    POSITIVE LOGITS
     feedback
    1.83
    FEEDBACK
    1.33
     Feedback
    1.23
    Feedback
    1.21
    feedback
    1.16
     feedbacks
    1.15
     spesso
    1.09
     clients
    1.04
     client
    1.04
     thanked
    1.02
    Activations Density 0.035%

    No Known Activations