© 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. 102754
    Prev
    Next
    INDEX
    Explanations

    you us me them

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

    The neuron flags second-person pronouns—especially “you”—used to directly address 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
     organizador
    -2.20
     土産
    -2.14
    ﺅ
    -2.06
     bordado
    -1.98
     bailarina
    -1.91
     camisetas
    -1.91
    lahir
    -1.85
    錞
    -1.81
     parfüm
    -1.78
     guerrero
    -1.77
    POSITIVE LOGITS
     to
    3.59
     eer
    1.95
     awe
    1.88
     able
    1.69
     serán
    1.66
     Provide
    1.64
    first
    1.62
     omin
    1.60
     eventual
    1.58
    на
    1.56
    Activations Density 0.017%

    No Known Activations