© 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. 3359
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on strong action verbs that describe procedural or policy operations (e.g. update, protect, determine, remedy).

    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
     أنها
    0.44
    ucked
    0.42
     banging
    0.41
     tenido
    0.41
     細
    0.41
    ूंगा
    0.40
     они
    0.40
    åg
    0.40
    strs
    0.39
     सुकून
    0.39
    POSITIVE LOGITS
     the
    0.64
     any
    0.58
     their
    0.54
     its
    0.50
     our
    0.49
     certain
    0.48
     or
    0.47
    而不是
    0.47
     existing
    0.47
    或
    0.47
    Activations Density 0.325%

    No Known Activations