© 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. 10-GEMMASCOPE-RES-131K
    7. 71273
    Prev
    Next
    INDEX
    Explanations

    Stalin, tribal

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

    The neuron activates on occurrences of the name “Stalin” (including within larger words like “Stalingrad”).

    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
    櫚
    -2.41
    This
    -2.41
    ",
    -2.33
    ?
    -2.33
    !
    -2.30
    榈
    -2.28
    '
    -2.27
    !!!!!!
    -2.23
    ,'
    -2.14
    一百
    -2.14
    POSITIVE LOGITS
    岨
    2.13
     VOUS
    2.05
    
    2.03
    
    2.00
     serán
    2.00
     punkt
    1.98
     maler
    1.98
     komfor
    1.98
     když
    1.96
     zato
    1.95
    Activations Density 0.001%

    No Known Activations