© 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. 72466
    Prev
    Next
    INDEX
    Explanations

    it followed by a verb

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

    The neuron strongly activates on the pronoun “it” (and its copular uses, as in “it is/was”).

    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
    m
    -1.94
    n
    -1.77
    k
    -1.75
    x
    -1.62
    r
    -1.59
    kl
    -1.59
    p
    -1.57
    ma
    -1.56
    c
    -1.55
     apparaissent
    -1.53
    POSITIVE LOGITS
    đầm
    1.64
     including
    1.59
    ambut
    1.57
    hijab
    1.55
    wolle
    1.52
    ciptakan
    1.52
     selanjutnya
    1.48
     formerly
    1.47
    Obr
    1.46
    Mua
    1.46
    Activations Density 0.083%

    No Known Activations