© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64344
    Prev
    Next
    INDEX
    Explanations

    demonstratives and then

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

    The neuron detects promotional call-to-action or persuasive marketing language addressed to the reader (e.g. “if you want…,” “look no further…,” “you want to…,” “then use this…”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     слишком
    -1.14
     beeind
    -1.02
     recientemente
    -1.01
    ebly
    -0.99
    жела
    -0.98
     spørs
    -0.98
    recently
    -0.96
    скільки
    -0.96
    opheles
    -0.95
     estudian
    -0.94
    POSITIVE LOGITS
     this
    2.56
    はこの
    1.52
    がこの
    1.39
    この
    1.35
     этого
    1.26
     here
    1.26
     этой
    1.26
     dieses
    1.20
     này
    1.20
     these
    1.16
    Activations Density 0.025%

    No Known Activations