© 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. 827
    Prev
    Next
    INDEX
    Explanations

    The neuron flags mentions of psychological/psychiatric disorders and related clinical‐style condition names.

    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
     ″
    0.64
     nessuna
    0.64
     hahaha
    0.63
     maakte
    0.63
     ecco
    0.61
     muziek
    0.58
     Ciebie
    0.58
     macchina
    0.57
     możesz
    0.57
     abbiamo
    0.57
    POSITIVE LOGITS
     socalled
    1.05
    
    0.95
        
    0.86
     }}$
    0.81
       
    0.78
    Downloaded
    0.77
     \\
    0.77
     }}^{\
    0.76
                                   
    0.75
         
    0.74
    Activations Density 1.375%

    No Known Activations