© 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. 50210
    Prev
    Next
    INDEX
    Explanations

    Toronto locations and entities

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

    The neuron strongly activates on tokens that occur at the beginnings of lines (including the leading indentation spaces).

    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
    ン
    -1.24
     iya
    -1.09
     tamil
    -1.05
     tenerife
    -1.02
    Taurus
    -1.00
     farà
    -0.96
     thomas
    -0.96
     ambayo
    -0.96
     promozione
    -0.96
    這個
    -0.95
    POSITIVE LOGITS
     Tuesdays
    1.40
    inage
    1.23
    ibles
    1.05
    reactstrap
    1.05
     また
    1.03
     Treats
    1.02
    edos
    1.02
    nology
    1.01
    vernment
    1.01
     defenses
    0.99
    Activations Density 0.327%

    No Known Activations