© 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. 22-GEMMASCOPE-RES-131K
    7. 14692
    Prev
    Next
    INDEX
    Explanations

    selection and award results

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

    The neuron detects words and phrases announcing or selecting winners (e.g. “winners,” “selected,” “will be announced,” “proposal selection notification”).

    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
     now
    -1.09
     lately
    -0.92
    [:,
    -0.89
    ͌
    -0.88
     شاهد
    -0.88
     input
    -0.85
    пка
    -0.85
    考
    -0.83
    客人
    -0.83
     sembra
    -0.82
    POSITIVE LOGITS
    Selected
    1.14
     awarded
    1.13
     selected
    1.02
    ॲ
    1.02
    getSelected
    1.02
    Auswahl
    1.01
    🧍
    1.00
     immediately
    1.00
     yf
    1.00
     SELECTED
    0.99
    Activations Density 0.018%

    No Known Activations