© 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. 21279
    Prev
    Next
    INDEX
    Explanations

    legal or sports contexts

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

    The neuron strongly activates on words that serve as formal titles or designations—e.g. organizational roles (“cadre”), honorifics/awards (“Stanley Cup,” “Hall of Fame”), and legal status terms (“Appellant,” “Respondent”).

    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
    ↵↵
    -1.62
    createCanvas
    -1.52
    ?’
    -1.50
    的女人
    -1.47
    5
    -1.46
    7
    -1.45
    孖
    -1.45
    在他的
    -1.41
    onshire
    -1.40
    zegovina
    -1.40
    POSITIVE LOGITS
    gencias
    1.76
    ︲
    1.70
     atriz
    1.60
    では
    1.48
    pegno
    1.48
     ensure
    1.48
     cantora
    1.47
     bilhões
    1.47
     describe
    1.45
    trás
    1.44
    Activations Density 0.057%

    No Known Activations