© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86270
    Prev
    Next
    INDEX
    Explanations

    actions done by me/us

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

    The neuron activates strongly on first-person pronouns (e.g. “me,” “us”).

    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>
    -1.76
     /
    -1.62
     ….
    -1.55
     contemplative
    -1.50
    what
    -1.48
     I
    -1.48
    /
    -1.45
     müssen
    -1.44
     beaute
    -1.44
    但却
    -1.41
    POSITIVE LOGITS
     jeste
    2.16
     budu
    2.14
     energii
    2.09
    鹇
    2.06
     stali
    2.00
     umy
    1.95
     okno
    1.95
     zape
    1.89
     upra
    1.88
     producent
    1.87
    Activations Density 0.008%

    No Known Activations