© 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. 90647
    Prev
    Next
    INDEX
    Explanations

    sighs, relief, tears, cheers, chuckle

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

    The neuron detects words naming expressive physical or emotional reactions (e.g. sigh, tears, jig, prayer, look).

    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
     this
    -1.70
     Following
    -1.59
     suavemente
    -1.48
     ligeramente
    -1.48
     Taking
    -1.48
     respiración
    -1.48
     Instead
    -1.46
     While
    -1.45
     краї
    -1.44
     only
    -1.43
    POSITIVE LOGITS
     of
    1.88
    푢
    1.60
    籥
    1.59
     metoda
    1.54
    providedIn
    1.51
     ſever
    1.51
    CastException
    1.51
     speciale
    1.50
    \":\"
    1.48
    @[+][
    1.46
    Activations Density 0.011%

    No Known Activations