© 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. 60652
    Prev
    Next
    INDEX
    Explanations

    Japanese and Chinese titles

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

    The neuron fires strongly on romanized Japanese words and names (e.g. titles, names, and terms written in Latin letters).

    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
     and
    -1.66
    ’
    -1.51
    Bereich
    -1.44
    übung
    -1.41
    ladung
    -1.39
    stätte
    -1.39
    listair
    -1.38
     I
    -1.37
    wanderung
    -1.37
    ではなく
    -1.36
    POSITIVE LOGITS
     considers
    1.67
    wanzig
    1.65
    akterysty
    1.63
    </h2>
    1.59
     dolorosa
    1.47
    </em>
    1.45
    ないので
    1.45
     includes
    1.44
     foule
    1.43
    ΠΟ
    1.43
    Activations Density 0.023%

    No Known Activations