© 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. 54257
    Prev
    Next
    INDEX
    Explanations

    like comparisons

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

    The neuron strongly activates on instances of the word “like” when it introduces a simile or comparative phrase.

    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
    2
    -1.56
    4
    -1.49
    9
    -1.41
     and
    -1.39
    3
    -1.36
    6
    -1.34
    felizmente
    -1.31
    inverno
    -1.31
    indahan
    -1.30
    5
    -1.29
    POSITIVE LOGITS
     a
    2.19
     an
    1.72
     putting
    1.49
     having
    1.38
     like
    1.33
     if
    1.28
     getting
    1.28
     being
    1.26
     taking
    1.23
     trying
    1.22
    Activations Density 0.014%

    No Known Activations