© 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. 34-GEMMASCOPE-RES-131K
    7. 59905
    Prev
    Next
    INDEX
    Explanations

    honorific titles and mentions

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

    The neuron detects honorifics and award‐related terms (titles and distinctions such as “Honorary,” “Hon.,” “Honored,” “Meritorious,” “decorated,” etc.).

    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
     honor
    -0.88
    ميم
    -0.81
     utilisées
    -0.77
     honour
    -0.77
    辕
    -0.76
     Honors
    -0.75
    婆
    -0.75
    >>();
    -0.74
    ồ
    -0.74
     usato
    -0.73
    POSITIVE LOGITS
     Mention
    1.20
     mention
    1.08
     mentions
    1.04
     doctorate
    0.99
    ބ
    0.98
    Mention
    0.94
     member
    0.93
    member
    0.90
     Mentions
    0.88
     citado
    0.85
    Activations Density 0.009%

    No Known Activations