© 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. 76243
    Prev
    Next
    INDEX
    Explanations

    take advantage or take care

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

    The neuron selectively activates on occurrences of the verb “take.”

    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
    ↵
    -1.45
     takes
    -1.34
     taking
    -1.19
    他的
    -1.18
    se
    -1.10
    r
    -1.08
    你的
    -1.08
    、
    -1.00
    s
    -1.00
    它的
    -1.00
    POSITIVE LOGITS
     advantage
    2.89
     care
    1.85
     refuge
    1.60
    advantage
    1.53
     away
    1.45
     into
    1.41
     käyttö
    1.41
     Abschied
    1.40
     apart
    1.37
     note
    1.33
    Activations Density 0.055%

    No Known Activations