© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9448
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on nominal tokens—identifying nouns (both common and proper).

    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
    e
    0.94
    1
    0.93
    te
    0.90
    R
    0.90
    0
    0.90
    ate
    0.87
    are
    0.87
      
    0.85
    N
    0.85
    V
    0.84
    POSITIVE LOGITS
    PanelVisual
    1.13
    TimeDict
    1.11
    ເທ
    1.05
    gmzy
    1.05
    تاریخ
    1.03
    nashvillehousing
    1.02
    MessageNow
    1.00
     txtbtn
    0.98
    𒆪
    0.96
    ចប់
    0.95
    Activations Density 0.000%

    No Known Activations