© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22026
    Prev
    Next
    INDEX
    Explanations

    ll followed by English or Chinese

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

    The neuron consistently activates on the character sequence “ll” (two lowercase L’s) 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
    阄
    -2.78
    葙
    -2.63
    懨
    -2.63
    ſelves
    -2.59
    絝
    -2.52
    憷
    -2.44
    ⸫
    -2.41
    ⑊
    -2.39
    ⚋
    -2.38
    the
    -2.34
    POSITIVE LOGITS
     was
    3.11
    {
    2.69
     We
    2.48
    ?"
    2.45
     and
    2.39
     Our
    2.39
     —
    2.38
     the
    2.38
    li
    2.28
     Are
    2.22
    Activations Density 0.001%

    No Known Activations