© 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. 74379
    Prev
    Next
    INDEX
    Explanations

    it followed by verb

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

    The neuron is primarily detecting occurrences of the pronoun “it.”

    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
     bandes
    -1.84
     rendement
    -1.83
    ||||
    -1.54
     vallen
    -1.53
     roues
    -1.49
     câbles
    -1.45
    ギュア
    -1.44
     colonnes
    -1.43
    нится
    -1.42
     hoor
    -1.41
    POSITIVE LOGITS
     also
    1.68
     including
    1.67
     sometimes
    1.66
     usually
    1.63
    ="
    1.59
     maybe
    1.59
     Mereka
    1.59
     then
    1.57
    This
    1.55
     should
    1.54
    Activations Density 0.083%

    No Known Activations