© 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. 73549
    Prev
    Next
    INDEX
    Explanations

    comic book titles and characters

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

    The neuron is responding to very high‐frequency/common tokens (function words and other very common words/punctuation).

    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
    REZ
    -0.85
     Mehl
    -0.76
    قيق
    -0.73
    angular
    -0.72
     Guadal
    -0.72
    polski
    -0.71
     angular
    -0.71
     conosciuto
    -0.70
    
    -0.69
    タン
    -0.69
    POSITIVE LOGITS
     Amazon
    0.90
    🦸
    0.87
     Butcher
    0.86
     Hug
    0.80
     BOYS
    0.80
     Alexa
    0.78
     Starlight
    0.77
     Boys
    0.77
    Amazon
    0.77
    浣
    0.77
    Activations Density 0.004%

    No Known Activations