© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102464
    Prev
    Next
    INDEX
    Explanations

    come to expect/know

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

    This neuron detects the stock reviewer phrase “you have (or you’ve) come to expect,” i.e. the “have come to expect” construction addressing 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_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
    颊
    -0.87
    nextInt
    -0.86
     Υ
    -0.81
    cidae
    -0.79
    fertigt
    -0.79
    desc
    -0.74
     downloads
    -0.74
    siasme
    -0.73
    edero
    -0.73
    guri
    -0.73
    POSITIVE LOGITS
     come
    1.59
     Come
    1.44
     came
    1.31
    Come
    1.26
     grown
    1.24
     became
    1.19
    come
    1.18
    COME
    1.05
     known
    1.05
     become
    1.04
    Activations Density 0.026%

    No Known Activations