© 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. 84264
    Prev
    Next
    INDEX
    Explanations

    slang for liking or enjoying

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

    The neuron is picking up on subjective stance markers—personal pronouns (you/we), negations, and intensifiers (really, totally, not)—that signal the author’s direct address or strong opinions.

    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
     dihasilkan
    -0.82
     dilaporkan
    -0.79
     ditentukan
    -0.78
     dialami
    -0.77
    TALK
    -0.75
    عب
    -0.74
    疮
    -0.74
    nbc
    -0.73
     kiện
    -0.73
    hete
    -0.72
    POSITIVE LOGITS
     dig
    4.63
     digs
    4.13
    Dig
    4.00
     digging
    3.91
     Dig
    3.89
    dig
    3.53
     DIG
    3.25
    DIG
    3.11
     dug
    2.81
     digger
    2.31
    Activations Density 0.048%

    No Known Activations