© 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. 35413
    Prev
    Next
    INDEX
    Explanations

    examples or instances

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

    The neuron fires on discourse markers that introduce examples or elaborations (e.g. “such as,” “for instance,” “in particular”).

    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
    立場
    -1.04
    bleshooting
    -0.93
    加以
    -0.90
     gewährleisten
    -0.86
    GRAPHY
    -0.85
     zwaar
    -0.85
    ・・・・・・・・
    -0.84
    殡
    -0.84
     celebr
    -0.83
    magini
    -0.83
    POSITIVE LOGITS
     behavior
    1.18
     behaviors
    1.14
     behaviours
    0.99
     behaviour
    0.96
     например
    0.96
     eating
    0.95
     self
    0.93
     coloridos
    0.93
     habits
    0.91
     például
    0.88
    Activations Density 0.083%

    No Known Activations