© 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. 5292
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on words that are action verbs (e.g. do, talk, used, did, drive, culminate).

    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
     гульнявыя
    0.88
     ойно
    0.86
     пово
    0.80
    ূন
    0.80
     skates
    0.80
    ⌵
    0.77
     bookings
    0.75
     galore
    0.75
     ойноо
    0.75
     نہيں
    0.74
    POSITIVE LOGITS
    }$
    0.94
    Product
    0.84
    XI
    0.82
    pre
    0.80
    A
    0.78
    La
    0.76
    Produ
    0.76
    }$$
    0.76
    Get
    0.75
    Pol
    0.75
    Activations Density 0.000%

    No Known Activations