© 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. 71967
    Prev
    Next
    INDEX
    Explanations

    discussion and conversation

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

    The neuron is triggered by very high-frequency “stop” tokens—common function words (e.g. “the,” “is,” “I,” “this,” “on”), punctuation (colons, commas, ellipses), and other ubiquitous elements (numbers, “thread”) rather than content words.

    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
    五郎
    -0.82
     alſo
    -0.80
     patatas
    -0.78
     %).
    -0.78
     første
    -0.78
    ringed
    -0.77
    鞏
    -0.77
     eux
    -0.77
     tưởng
    -0.76
    곽
    -0.76
    POSITIVE LOGITS
     discussion
    1.28
     discussing
    1.16
     topic
    1.03
    discuss
    1.02
     discussions
    1.02
     conversation
    1.02
     topics
    1.02
     débat
    1.00
    讨论
    0.96
    discus
    0.93
    Activations Density 0.010%

    No Known Activations