© 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. 10-GEMMASCOPE-RES-131K
    7. 130446
    Prev
    Next
    INDEX
    Explanations

    negative emotions and events

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

    The neuron flags strong negative‐emotion words (e.g. dismaying, disheartening, appalling, horrified, distraught).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    s
    -2.52
    h
    -2.02
    は
    -1.93
    деи
    -1.90
    A
    -1.88
    K
    -1.87
     Когда
    -1.80
    N
    -1.79
    O
    -1.77
    If
    -1.76
    POSITIVE LOGITS
    膘
    2.20
    齶
    2.13
    死的
    2.09
     всички
    2.02
    ῞
    2.02
    仉
    1.95
     milyen
    1.94
    发生的
    1.92
    
    1.91
    ↵↵
    1.90
    Activations Density 0.007%

    No Known Activations