© 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. 127778
    Prev
    Next
    INDEX
    Explanations

    you and someone else

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

    The neuron activates on second‐person references—especially “you” and “your”—i.e. direct address to the reader.

    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
    </em>
    -2.94
    </h4>
    -1.91
     huge
    -1.84
    ～～
    -1.75
     two
    -1.74
     uzyskać
    -1.72
     for
    -1.71
    i
    -1.70
     first
    -1.66
     varias
    -1.66
    POSITIVE LOGITS
    躋
    1.97
    夘
    1.91
    </h1>
    1.78
     prong
    1.70
     dévelo
    1.68
    primarily
    1.67
     exposé
    1.66
    ’?
    1.65
     vectorstock
    1.65
    pected
    1.64
    Activations Density 0.014%

    No Known Activations