© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73247
    Prev
    Next
    INDEX
    Explanations

    universities and academic institutions

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

    The neuron flags mentions of formal institutions—especially universities, colleges, and schools.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     jahre
    -1.95
     VERY
    -1.91
    〟
    -1.84
    
    -1.82
     nuove
    -1.78
     δεν
    -1.78
    潆
    -1.78
    大概是
    -1.76
    庹
    -1.76
     bestehende
    -1.75
    POSITIVE LOGITS
     if
    2.14
    ]
    1.99
    ):
    1.96
    a
    1.81
     r
    1.75
     cedera
    1.73
    个
    1.70
    e
    1.60
    m
    1.59
     two
    1.58
    Activations Density 0.005%

    No Known Activations