© 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. 12949
    Prev
    Next
    INDEX
    Explanations

    names ending in cy/acy

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

    The neuron strongly activates on capitalized proper names—brand names and personal surnames.

    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
     You
    -2.67
    </strong>
    -2.61
    浤
    -2.50
    淠
    -2.44
     összefoglal
    -2.44
    ciutto
    -2.39
     Many
    -2.38
    阋
    -2.34
    玏
    -2.31
    ⢊
    -2.30
    POSITIVE LOGITS
    >
    2.67
    '
    2.41
    i
    2.22
    I
    2.16
     самая
    2.16
    ネットで
    2.11
    x
    2.11
     dilemma
    2.09
    al
    2.08
     puis
    2.06
    Activations Density 0.003%

    No Known Activations