© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84201
    Prev
    Next
    INDEX
    Explanations

    graduate programs and degrees

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

    The neuron is primarily picking up very high‐frequency function words (common stopwords) such as “to,” “of,” “the,” and other ubiquitous tokens.

    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
     teen
    -1.02
    Undergraduate
    -0.97
     teenage
    -0.94
     Undergraduate
    -0.92
     undergraduate
    -0.85
     GCSE
    -0.85
     teenagers
    -0.83
     Sophomore
    -0.83
     Teen
    -0.81
     teens
    -0.79
    POSITIVE LOGITS
     Graduate
    2.08
    Graduate
    1.95
     graduate
    1.95
     doctoral
    1.33
     GRE
    1.30
     PhD
    1.29
    graduate
    1.27
     masters
    1.25
     grad
    1.23
     GRADUATE
    1.23
    Activations Density 0.045%

    No Known Activations