© 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. 22-GEMMASCOPE-RES-131K
    7. 130290
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to the standalone pronoun “It,” especially when it appears at the start of a sentence or clause.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    It followed by common verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    鱂
    -2.36
    fordshire
    -2.28
    鱨
    -2.06
    什么事
    -2.03
     rigue
    -1.99
     電車
    -1.91
     hadden
    -1.90
     membag
    -1.88
     memutus
    -1.86
     vrouw
    -1.85
    POSITIVE LOGITS
     was
    3.20
     wasn
    2.66
     It
    2.61
     is
    2.44
    ]
    2.25
     didn
    2.19
     isn
    2.17
    ’
    2.11
     
    1.93
     hasn
    1.91
    Activations Density 0.279%

    No Known Activations