© 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. 6875
    Prev
    Next
    INDEX
    Explanations

    The neuron flags occurrences of uppercase acronym fragments (letters or letter‐groups) often appearing in parentheses or as acronym components.

    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
     Γ
    0.70
     הג
    0.58
     Π
    0.52
     הפ
    0.52
     И
    0.52
     ebenfalls
    0.49
     GCC
    0.49
     QS
    0.48
     У
    0.47
     Holi
    0.47
    POSITIVE LOGITS
     acronym
    1.41
     abbreviation
    1.38
     siglas
    1.20
     abbreviations
    1.11
    stands
    1.09
     Stands
    1.02
     initials
    1.00
     Abbreviations
    0.98
    Abbreviations
    0.92
     stands
    0.86
    Activations Density 0.526%

    No Known Activations