© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38330
    Prev
    Next
    INDEX
    Explanations

    then

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

    The neuron fires strongly on direct requests or instructions addressed to the reader (e.g. “I want you to…,” “Maybe you could tell me…,” “Can you help…”).

    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
     now
    -1.08
     agora
    -1.07
     désormais
    -1.02
     теперь
    -0.99
    Now
    -0.96
     pouvaient
    -0.94
     اکنون
    -0.94
     nyt
    -0.93
     agres
    -0.92
     didn
    -0.91
    POSITIVE LOGITS
     then
    2.94
     will
    2.33
     THEN
    1.80
     thereafter
    1.74
     afterwards
    1.65
     later
    1.61
     затем
    1.58
    その後
    1.55
     Thereafter
    1.54
     Then
    1.52
    Activations Density 0.082%

    No Known Activations