© 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. 39369
    Prev
    Next
    INDEX
    Explanations

    aws

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

    The neuron strongly activates on the character sequence “aw” within tokens.

    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
     และ
    -2.98
    榈
    -2.88
    vantaged
    -2.75
    ,’
    -2.70
     должна
    -2.64
    öpfer
    -2.58
    麈
    -2.55
    できる
    -2.47
     แต่
    -2.45
    櫚
    -2.44
    POSITIVE LOGITS
    aw
    3.73
    ing
    3.30
    2
    3.14
    8
    3.05
    *
    2.75
    ኧ
    2.67
    ?
    2.61
    ed
    2.59
    =
    2.59
    ↵↵
    2.45
    Activations Density 0.012%

    No Known Activations