© 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. 22-GEMMASCOPE-RES-131K
    4. 35708
    Prev
    Next
    INDEX
    Explanations

    quoted words or phrases

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

    The neuron fires on text enclosed in double quotation marks.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    The
    -2.20
    
    -2.00
    镲
    -1.98
    </h2>
    -1.94
     indépendant
    -1.88
     conster
    -1.86
    衕
    -1.85
    鹇
    -1.85
     ち
    -1.80
    そういえば
    -1.76
    POSITIVE LOGITS
     and
    2.53
     or
    2.30
     that
    2.11
    ."
    2.00
     "
    1.90
     for
    1.88
     at
    1.81
    đầm
    1.74
    slavery
    1.73
     which
    1.68
    Activations Density 0.133%

    No Known Activations