© 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. 15345
    Prev
    Next
    INDEX
    Explanations

    proper names

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

    The neuron detects repeated mentions of the same proper name across a document, with its activation decaying on each subsequent occurrence.

    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
     він
    -2.66
     也
    -2.48
    縺
    -2.45
     жк
    -2.45
    とりあえず
    -2.23
     сказал
    -2.23
    desertcart
    -2.23
     xadrez
    -2.23
    sandalia
    -2.22
    驁
    -2.22
    POSITIVE LOGITS
    to
    3.31
    o
    3.17
    ar
    2.91
    k
    2.88
    —
    2.81
    x
    2.78
    y
    2.72
     пев
    2.63
    =
    2.61
    M
    2.44
    Activations Density 0.003%

    No Known Activations