© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1855
    Prev
    Next
    INDEX
    Explanations

    nice chatting with you

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

    The neuron specializes in spotting first‐person expressions of personal honor, gratitude, or privilege (e.g. “I feel it is a privilege to serve,” “It is very gratifying,” “I am honored”).

    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
     раздра
    0.65
    }}]
    0.64
    }}$
    0.64
    צי
    0.61
     disappro
    0.60
     irritated
    0.60
     craw
    0.59
     irritability
    0.59
     loopholes
    0.59
    👎
    0.59
    POSITIVE LOGITS
     privilege
    2.19
     pleasure
    2.00
     Privilege
    1.88
     privilegio
    1.80
     Pleasure
    1.75
     honored
    1.74
     honoured
    1.74
     honor
    1.72
     privileged
    1.68
     honour
    1.67
    Activations Density 0.637%

    No Known Activations