© 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. 10-GEMMASCOPE-RES-131K
    7. 110562
    Prev
    Next
    INDEX
    Explanations

    And, followed by conjunctions

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

    The neuron never activates—it doesn’t pick out any pattern or feature in the text.

    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
    3
    -2.30
    5
    -2.14
    4
    -2.06
    2
    -2.00
     only
    -1.92
    8
    -1.85
    1
    -1.83
    9
    -1.81
     gdyż
    -1.75
     is
    -1.70
    POSITIVE LOGITS
    romeda
    2.17
     raiſ
    1.85
     dermed
    1.77
    蹚
    1.76
     milj
    1.76
     拌
    1.75
    悒
    1.73
    sses
    1.72
     券
    1.70
     osal
    1.66
    Activations Density 0.016%

    No Known Activations