© 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. 780
    Prev
    Next
    INDEX
    Explanations

    This neuron is tuned to detect the colon punctuation character “:”.

    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
    Otros
    0.76
    ও
    0.71
    Also
    0.66
    ก็ตาม
    0.62
    (?)
    0.61
     కూడా
    0.61
    Pero
    0.60
    도
    0.59
    Then
    0.59
    Anyways
    0.59
    POSITIVE LOGITS
     namely
    1.23
     yakni
    1.14
     nämlich
    1.14
     Namely
    1.09
     namelijk
    0.98
     yaitu
    0.98
    namely
    0.96
     totiž
    0.94
     While
    0.92
    一是
    0.90
    Activations Density 0.462%

    No Known Activations