© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106972
    Prev
    Next
    INDEX
    Explanations

    pull off difficult things

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

    The neuron fires on instances of the phrasal verb “pull off” (and its inflected forms) when describing accomplishing or executing something tricky.

    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
    Ｊ
    -0.78
    DBHelper
    -0.76
     filós
    -0.75
    ète
    -0.73
     roomId
    -0.72
    娉
    -0.72
    paymentMethod
    -0.72
    縁
    -0.71
    搦
    -0.70
     ::=
    -0.70
    POSITIVE LOGITS
     pull
    4.66
    pull
    4.38
     Pull
    4.13
     pulled
    4.09
    Pull
    4.03
     pulls
    3.91
     pulling
    3.81
    Pulling
    3.45
    pulled
    3.34
    PULL
    3.23
    Activations Density 0.054%

    No Known Activations