© 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. 55848
    Prev
    Next
    INDEX
    Explanations

    said, like, was

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

    The neuron detects colloquial quotative “like” constructions (e.g. “I’m like,” “he’s like,” “you’re like”) used to introduce speech or reaction.

    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
    ϲ
    -0.86
    progressDialog
    -0.84
    верь
    -0.84
    防災
    -0.82
     fornito
    -0.82
     Sugges
    -0.81
    ↵
    -0.80
    jenie
    -0.79
    aterna
    -0.79
    ȴ
    -0.79
    POSITIVE LOGITS
     like
    1.82
     said
    1.38
     goes
    1.27
     be
    1.21
     was
    1.18
    Like
    1.14
     такие
    1.09
     такая
    1.09
     going
    1.02
     như
    1.01
    Activations Density 0.014%

    No Known Activations