© 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. 103637
    Prev
    Next
    INDEX
    Explanations

    learning skills, methods, techniques

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on uncommon, domain-specific tokens (rare or specialized terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     = 
    -0.94
     geological
    -0.90
    いで
    -0.84
    appointed
    -0.81
    triangle
    -0.81
    隹
    -0.79
     проекта
    -0.79
     palette
    -0.79
    abond
    -0.78
     Inggris
    -0.76
    POSITIVE LOGITS
     techniques
    1.13
     method
    1.05
     practice
    1.04
     learned
    1.01
    īm
    0.99
     skills
    0.99
     practiced
    0.98
     technique
    0.97
     methods
    0.93
     comprehend
    0.93
    Activations Density 0.003%

    No Known Activations