© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19367
    Prev
    Next
    INDEX
    Explanations

    you or they

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

    The neuron fires on promotional or instructional wording that emphasizes benefits, needs, or actions (e.g. persuasive “you/your,” “need,” “can,” “using,” etc.).

    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
     while
    -1.76
     those
    -1.72
     one
    -1.63
     with
    -1.60
     and
    -1.42
     as
    -1.38
     intricacies
    -1.37
     would
    -1.35
     three
    -1.34
     nine
    -1.34
    POSITIVE LOGITS
     you
    2.23
     your
    2.00
    あなた
    1.83
    おわりに
    1.82
    ↵↵↵↵
    1.73
    あなたが
    1.73
     podrás
    1.69
    ↵↵↵
    1.67
    Puedes
    1.63
     GOtt
    1.60
    Activations Density 0.477%

    No Known Activations