© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66398
    Prev
    Next
    INDEX
    Explanations

    years ago, numbers

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

    The neuron strongly activates on mentions of professional baseball player names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    után
    -0.91
    braith
    -0.90
    وانید
    -0.84
    よろしくお願いいたします
    -0.83
    wsze
    -0.82
    拽
    -0.79
    adaran
    -0.79
     ťaž
    -0.79
    เขา
    -0.79
    途中で
    -0.79
    POSITIVE LOGITS
    basedir
    0.87
    第二
    0.82
    (>
    0.80
    giendo
    0.78
    prnt
    0.77
    舟
    0.77
     roadside
    0.77
    tank
    0.76
     seem
    0.76
     = 
    0.75
    Activations Density 0.442%

    No Known Activations