© 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. 22-GEMMASCOPE-RES-131K
    7. 36008
    Prev
    Next
    INDEX
    Explanations

    whether, if, and how to do

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

    The neuron spikes on second‐person, reader‐addressing terms—especially “you” and interrogative words (who, what, whether)—i.e. question or instruction contexts directed at the reader.

    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
    こんばんは
    -1.02
     latter
    -1.01
    服务的
    -1.00
    되지
    -1.00
    usually
    -0.99
    often
    -0.98
    generally
    -0.98
     hardly
    -0.98
    couldn
    -0.98
     acceptez
    -0.97
    POSITIVE LOGITS
     your
    2.47
    可能
    1.55
     if
    1.53
     you
    1.47
     before
    1.43
     possible
    1.31
     yourself
    1.25
    rillation
    1.23
     potential
    1.16
     how
    1.15
    Activations Density 0.025%

    No Known Activations