© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20415
    Prev
    Next
    INDEX
    Explanations

    pulling and traction

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

    The neuron activates strongly on words describing pulling, tugging, or drawing forces (e.g., tug, yank, pull, traction).

    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
     may
    -1.55
    仍然
    -1.38
     leggero
    -1.37
     subtly
    -1.34
     might
    -1.30
     increased
    -1.29
    On
    -1.28
     did
    -1.28
    although
    -1.27
     ufficiali
    -1.24
    POSITIVE LOGITS
    鰱
    1.52
    泚
    1.52
    yatı
    1.50
    taan
    1.49
    viembre
    1.48
    尨
    1.46
    妧
    1.44
    pulled
    1.44
    </td>
    1.43
    妗
    1.42
    Activations Density 0.069%

    No Known Activations