© 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. 30575
    Prev
    Next
    INDEX
    Explanations

    verbs followed by through

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

    The neuron fires on verbs (and the word “through” itself) when they appear together in phrasal-verb constructions expressing movement or passage “through” something (e.g. slip through, run through, slice through, pass through).

    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
    сса
    -0.96
    帰り
    -0.94
    Ered
    -0.85
     棚
    -0.77
    IntegerField
    -0.76
     mouseClicked
    -0.76
    izien
    -0.76
    unjukkan
    -0.75
    goto
    -0.74
     แบบ
    -0.73
    POSITIVE LOGITS
     through
    8.88
    Through
    6.00
    through
    5.94
     через
    5.63
     Through
    5.47
     attraverso
    5.25
     melalui
    4.91
     através
    4.91
     THROUGH
    4.88
    THROUGH
    4.78
    Activations Density 0.400%

    No Known Activations