© 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. 22-GEMMASCOPE-RES-131K
    7. 79743
    Prev
    Next
    INDEX
    Explanations

    emotional states and experiences

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

    The neuron strongly activates on occurrences of the word “emotional.”

    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
     It
    -2.67
     These
    -2.56
     You
    -2.52
    UCIÓN
    -2.52
     This
    -2.31
    ';
    -2.25
     Please
    -2.22
    .”
    -2.20
     ofrecerte
    -2.19
     resulting
    -2.14
    POSITIVE LOGITS
    1
    2.53
    ↵↵
    2.45
    n
    2.44
    「
    2.39
    .
    2.33
    {
    2.31
    ↵
    2.17
    みそ
    2.03
    쩡
    1.95
    味噌汁
    1.85
    Activations Density 0.010%

    No Known Activations