© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3461
    Prev
    Next
    INDEX
    Explanations

    friendship and sharing intimacy

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

    The neuron specifically activates on phrases about getting to know someone (establishing personal acquaintance).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     nays
    0.52
     pessim
    0.51
    ouncements
    0.50
     sèche
    0.50
     Forward
    0.50
     unsatisfied
    0.49
    兌
    0.49
    兑
    0.48
     Dad
    0.48
     اعتراض
    0.47
    POSITIVE LOGITS
     friendship
    1.97
     befri
    1.73
     বন্ধুত্ব
    1.72
     amistad
    1.72
     friendships
    1.70
     Friendship
    1.63
     intimacy
    1.59
     दोस्ती
    1.46
     friendliness
    1.46
     मित्रता
    1.44
    Activations Density 0.669%

    No Known Activations