© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 352
    Prev
    Next
    INDEX
    Explanations

    pronouns refer to self or others

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

    The neuron fires on personal, participant-referencing pronouns and related words (e.g. “I,” “me,” “you,” “us,” “him,” “here,” “one”), marking direct speaker/audience references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.59
    1
    0.41
    0
    0.39
    -
    0.39
    5
    0.38
    8
    0.37
    4
    0.36
    ↵
    0.36
    2
    0.35
    6
    0.35
    POSITIVE LOGITS
    StoredKeys
    0.43
     persönlich
    0.40
    ſelf
    0.39
    ្នុង
    0.39
    eredith
    0.39
    zelf
    0.39
    ಲೆಯ
    0.39
     Bacteriol
    0.38
    squarePos
    0.38
    EnglishMarks
    0.38
    Activations Density 0.873%

    No Known Activations