© 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. 48129
    Prev
    Next
    INDEX
    Explanations

    expressing interest in something

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

    The neuron detects instances of the phrase “interested in” that introduce invitations or calls to action.

    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
     neuen
    -1.82
    What
    -1.60
     wyja
    -1.50
     people
    -1.50
     größere
    -1.48
     each
    -1.48
     powiedział
    -1.47
    Informazioni
    -1.43
     dokładnie
    -1.41
     potwier
    -1.41
    POSITIVE LOGITS
    蚡
    1.73
     licht
    1.66
     dage
    1.55
    ーズン
    1.53
     nimmer
    1.52
     alho
    1.50
    哪
    1.49
     utro
    1.48
     niks
    1.47
     flink
    1.45
    Activations Density 0.009%

    No Known Activations