© 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. 10-GEMMASCOPE-RES-131K
    7. 67577
    Prev
    Next
    INDEX
    Explanations

    hook up or connection

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

    This neuron strongly activates on instances of the phrase “hook up.”

    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
    ある
    -1.91
    𐐪
    -1.82
     "}";
    -1.74
     ながら
    -1.67
    琑
    -1.66
    Ｘ
    -1.64
    e
    -1.63
     anny
    -1.63
    哒
    -1.61
    你在
    -1.60
    POSITIVE LOGITS
    ]
    2.02
    ,’”
    1.77
     envisaged
    1.75
    ?’
    1.70
     firstly
    1.69
     Notably
    1.67
    之时
    1.66
    atuur
    1.66
     ―
    1.65
     Firstly
    1.63
    Activations Density 0.004%

    No Known Activations