© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6898
    Prev
    Next
    INDEX
    Explanations

    I can't / I am obligated

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

    The neuron strongly activates on occurrences of the first‐person plural pronoun “we” (and related official‐speaker subjects like “officials,” “police,” etc.), i.e. statements voiced by an authoritative “we.”

    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_31_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
    私たち
    0.93
     OUR
    0.84
    Our
    0.78
    OUR
    0.74
     हमारा
    0.74
    私たちの
    0.74
     हमारी
    0.73
    Unsere
    0.71
     ourselves
    0.71
    আমাদের
    0.71
    POSITIVE LOGITS
     commits
    0.78
     committed
    0.75
     प्रतिबद्ध
    0.75
     Commitment
    0.70
     thấy
    0.67
    commits
    0.66
     commit
    0.65
     beachten
    0.65
     Committed
    0.65
     commitment
    0.64
    Activations Density 0.154%

    No Known Activations