© 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. 10-GEMMASCOPE-RES-131K
    7. 20692
    Prev
    Next
    INDEX
    Explanations

    Ai or Ay beginnings

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

    The neuron detects the letter bigram “ai” (in any casing) within individual 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
    ’
    -3.38
    ”
    -2.86
    l
    -2.75
    a
    -2.72
    ’，
    -2.72
    ”,
    -2.72
    i
    -2.66
    𖡼
    -2.59
     “
    -2.44
    ”:
    -2.39
    POSITIVE LOGITS
    {
    3.20
     are
    3.16
    ?"
    2.88
    ..."
    2.70
     finds
    2.64
     dizem
    2.47
     shines
    2.45
    --"
    2.41
     simplifies
    2.39
    簠
    2.39
    Activations Density 0.005%

    No Known Activations