© 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. 34-GEMMASCOPE-RES-131K
    7. 58961
    Prev
    Next
    INDEX
    Explanations

    Honors programs and writing courses

    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_34/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
     Playoffs
    -0.80
     Postgraduate
    -0.79
     Pinus
    -0.79
    ghed
    -0.79
     paloma
    -0.77
     Hwy
    -0.73
    ΟΝ
    -0.73
     sensorial
    -0.72
     ote
    -0.70
     Michaelis
    -0.70
    POSITIVE LOGITS
     Honors
    1.16
     honors
    1.02
     Inquiry
    0.96
     exclusivas
    0.89
     Theme
    0.87
     Experience
    0.85
     enriched
    0.83
    Honors
    0.82
     inquiry
    0.82
     clusters
    0.82
    Activations Density 0.026%

    No Known Activations