© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 3398
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on enthusiastic, emphatic personal testimonials and calls-to-action—informal first- or second-person expressions (e.g. “I was there,” “go and grab it,” “don’t wait,” “it’s that good!”).

    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
     badass
    1.14
     tbh
    0.98
     lmao
    0.98
     (~
    0.98
     (‘
    0.97
     근데
    0.96
    Haha
    0.95
     („
    0.95
     haha
    0.93
     (“
    0.93
    POSITIVE LOGITS
     IMHO
    0.89
     !!!!!
    0.84
     !!!!
    0.82
    不但
    0.78
    埸
    0.77
    !!!!
    0.77
    !!!!!
    0.76
    !!!!!!!!!!!!!!!!
    0.74
     muß
    0.74
       
    0.73
    Activations Density 0.439%

    No Known Activations