© 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. 22-GEMMASCOPE-RES-131K
    4. 39450
    Prev
    Next
    INDEX
    Explanations

    forming common phrases

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

    The neuron is triggered by specialized scientific or biochemical terms (e.g., protein/receptor names, enzyme and pathway components, molecular or cellular entities).

    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
     lettura
    -1.14
     mangá
    -1.08
     vestido
    -1.06
    eburger
    -1.05
     masculino
    -1.04
     cruzado
    -1.02
    tros
    -0.99
    engers
    -0.99
    اتر
    -0.98
    倦
    -0.98
    POSITIVE LOGITS
    <bos>
    1.29
     എന്ന
    1.20
     Hinsicht
    1.07
     '';
    1.05
    跻
    1.01
    woners
    1.00
    但却
    1.00
     '';
    
    0.98
    って思
    0.97
     quaisquer
    0.96
    Activations Density 0.412%

    No Known Activations