© 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. 10-GEMMASCOPE-RES-131K
    7. 47566
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

    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_10/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
    In
    -2.36
    葙
    -2.16
    \
    -2.08
    ใน
    -1.97
    呖
    -1.97
     phénom
    -1.88
     correctes
    -1.80
            
    -1.80
     conva
    -1.77
    鲥
    -1.75
    POSITIVE LOGITS
     was
    1.93
    section
    1.84
    2
    1.76
     δύο
    1.66
    </b>
    1.65
     which
    1.58
    which
    1.58
     ursprünglich
    1.55
    鴬
    1.52
    遭受
    1.51
    Activations Density 0.146%

    No Known Activations