© 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. 89976
    Prev
    Next
    INDEX
    Explanations

    Steve followed by a name

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

    The neuron detects occurrences of the proper name “Steve.”

    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
     Both
    -0.86
    讀書
    -0.85
     kriminal
    -0.84
    文案
    -0.83
    fehl
    -0.83
    本当の
    -0.82
    世间
    -0.81
    実感
    -0.81
    Boys
    -0.81
     visually
    -0.81
    POSITIVE LOGITS
     Jobs
    1.30
     {
    
    1.09
     Spielberg
    1.03
    )));
    
    1.02
    ienti
    1.01
     jobs
    0.99
     Vai
    0.98
    Jobs
    0.98
    endimento
    0.96
     ___________
    0.96
    Activations Density 0.011%

    No Known Activations