© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41762
    Prev
    Next
    INDEX
    Explanations

    I and possessive pronouns

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

    The neuron is tuned to words that signal personal, subjective expression—pronouns (“I”), modals (“would”), opinion verbs (“think,” “like”), and sentiment markers (“love,” “baby”) that mark a personal viewpoint.

    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
     fellow
    -1.40
    ffion
    -1.18
    cznym
    -1.16
     erforder
    -1.15
     informée
    -1.13
    cestor
    -1.09
     decorados
    -1.09
    ário
    -1.09
     یا
    -1.08
    ℬ
    -1.07
    POSITIVE LOGITS
    医药
    1.17
     himself
    1.17
     who
    1.14
    ⋗
    1.11
     whom
    1.01
    だったが
    1.00
     immense
    0.99
    些
    0.98
     душу
    0.97
     again
    0.97
    Activations Density 0.051%

    No Known Activations