© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129646
    Prev
    Next
    INDEX
    Explanations

    describing similarity with "like"

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

    The neuron detects comparative or similative expressions (e.g. “like,” “such as,” “のような,” “怎样”) that introduce examples or likenesses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    猡
    -2.77
    ⃚
    -2.33
    ???:
    -2.13
    裢
    -2.11
    lamps
    -2.06
    砹
    -2.03
    挲
    -1.96
    🕺
    -1.96
    ichteten
    -1.95
     Muitos
    -1.93
    POSITIVE LOGITS
    5
    2.42
    6
    2.30
    Also
    2.20
    “
    2.20
    3
    2.14
    1
    2.08
     {
    2.00
    Another
    1.97
    0
    1.97
    7
    1.82
    Activations Density 0.004%

    No Known Activations