© 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. 22-GEMMASCOPE-RES-131K
    7. 95502
    Prev
    Next
    INDEX
    Explanations

    institution and institutional

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

    The neuron activates on occurrences of the word “institution” (and its morphological variants like “institutional” or “institutions”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    雱
    -3.05
    螣
    -2.59
     freaking
    -2.53
    蹰
    -2.28
    
    -2.25
     Erinnerungen
    -2.23
    linawan
    -2.16
     lamented
    -2.16
    ʯ
    -2.16
     但
    -2.14
    POSITIVE LOGITS
    ’
    3.23
    </h4>
    3.09
    ）
    2.83
    ஂ
    2.67
    ”)
    2.56
    {
    2.56
    ]
    2.48
    g
    2.45
    ’’
    2.39
    酝
    2.22
    Activations Density 0.006%

    No Known Activations