© 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. 8854
    Prev
    Next
    INDEX
    Explanations

    This neuron detects first-person descriptions of receiving support or care from a group or community.

    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
     loophole
    0.97
     unsustainable
    0.91
     loopholes
    0.89
     vaguely
    0.88
     bloated
    0.86
     prohibitive
    0.85
     corpses
    0.84
    噱
    0.84
     pointless
    0.81
     hallucin
    0.81
    POSITIVE LOGITS
     Helped
    1.24
     Leadership
    1.08
     تعلمنا
    0.99
     Mentor
    0.98
     giúp
    0.96
    inspir
    0.96
    協助
    0.93
     invaluable
    0.93
     helped
    0.93
     mentor
    0.93
    Activations Density 1.116%

    No Known Activations