© 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. 34-GEMMASCOPE-RES-131K
    7. 75566
    Prev
    Next
    INDEX
    Explanations

    accepted, welcome, needed, required

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

    The neuron strongly responds to auxiliary-verb forms of “be” or “will” (e.g. are, being, will be) that signal passive or future constructions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     DriverManager
    -0.81
     pét
    -0.73
     CascadeType
    -0.71
     disponib
    -0.71
    ImageView
    -0.71
    萩
    -0.70
     fontsize
    -0.70
     شع
    -0.69
     LETTER
    -0.69
     связан
    -0.69
    POSITIVE LOGITS
     sought
    3.58
     wanted
    2.69
     needed
    2.44
     Wanted
    2.28
     desired
    2.20
    wanted
    2.14
     solicited
    2.13
     Needed
    2.08
    Wanted
    2.06
     awaited
    2.03
    Activations Density 0.111%

    No Known Activations